Stop the war!Остановите войну!
for scientists:
default search action
Google
Google Scholar
Semantic Scholar
Internet Archive Scholar
CiteSeerX
ORCIDBibTeX records: Csaba Szepesvári
@article{DBLP:journals/corr/abs-2402-17235,
author = {Jincheng Mei and
Zixin Zhong and
Bo Dai and
Alekh Agarwal and
Csaba Szepesv{\'{a}}ri and
Dale Schuurmans},
title = {Stochastic Gradient Succeeds for Bandits},
journal = {CoRR},
volume = {abs/2402.17235},
year = {2024},
url = {https://doi.org/10.48550/arXiv.2402.17235},
doi = {10.48550/ARXIV.2402.17235},
eprinttype = {arXiv},
eprint = {2402.17235},
timestamp = {Mon, 25 Mar 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2402-17235.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2403-05385,
author = {Alex Ayoub and
Kaiwen Wang and
Vincent Liu and
Samuel Robertson and
James McInerney and
Dawen Liang and
Nathan Kallus and
Csaba Szepesv{\'{a}}ri},
title = {Switching the Loss Reduces the Cost in Batch Reinforcement Learning},
journal = {CoRR},
volume = {abs/2403.05385},
year = {2024},
url = {https://doi.org/10.48550/arXiv.2403.05385},
doi = {10.48550/ARXIV.2403.05385},
eprinttype = {arXiv},
eprint = {2403.05385},
timestamp = {Thu, 04 Apr 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2403-05385.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2403-10379,
author = {Johannes Kirschner and
Seyed Alireza Bakhtiari and
Kushagra Chandak and
Volodymyr Tkachuk and
Csaba Szepesv{\'{a}}ri},
title = {Regret Minimization via Saddle Point Optimization},
journal = {CoRR},
volume = {abs/2403.10379},
year = {2024},
url = {https://doi.org/10.48550/arXiv.2403.10379},
doi = {10.48550/ARXIV.2403.10379},
eprinttype = {arXiv},
eprint = {2403.10379},
timestamp = {Mon, 08 Apr 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2403-10379.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aistats/TkachukBKJBS23,
author = {Volodymyr Tkachuk and
Seyed Alireza Bakhtiari and
Johannes Kirschner and
Matej Jusup and
Ilija Bogunovic and
Csaba Szepesv{\'{a}}ri},
editor = {Francisco J. R. Ruiz and
Jennifer G. Dy and
Jan{-}Willem van de Meent},
title = {Efficient Planning in Combinatorial Action Spaces with Applications
to Cooperative Multi-Agent Reinforcement Learning},
booktitle = {International Conference on Artificial Intelligence and Statistics,
25-27 April 2023, Palau de Congressos, Valencia, Spain},
series = {Proceedings of Machine Learning Research},
volume = {206},
pages = {6342--6370},
publisher = {{PMLR}},
year = {2023},
url = {https://proceedings.mlr.press/v206/tkachuk23a.html},
timestamp = {Mon, 19 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/aistats/TkachukBKJBS23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/colt/LiuMKLWS23,
author = {Sihan Liu and
Gaurav Mahajan and
Daniel Kane and
Shachar Lovett and
Gell{\'{e}}rt Weisz and
Csaba Szepesv{\'{a}}ri},
editor = {Gergely Neu and
Lorenzo Rosasco},
title = {Exponential Hardness of Reinforcement Learning with Linear Function
Approximation},
booktitle = {The Thirty Sixth Annual Conference on Learning Theory, {COLT} 2023,
12-15 July 2023, Bangalore, India},
series = {Proceedings of Machine Learning Research},
volume = {195},
pages = {1588--1617},
publisher = {{PMLR}},
year = {2023},
url = {https://proceedings.mlr.press/v195/liu23b.html},
timestamp = {Tue, 09 Apr 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/colt/LiuMKLWS23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iclr/Zheng0QFYSW23,
author = {Sirui Zheng and
Lingxiao Wang and
Shuang Qiu and
Zuyue Fu and
Zhuoran Yang and
Csaba Szepesv{\'{a}}ri and
Zhaoran Wang},
title = {Optimistic Exploration with Learned Features Provably Solves Markov
Decision Processes with Neural Dynamics},
booktitle = {The Eleventh International Conference on Learning Representations,
{ICLR} 2023, Kigali, Rwanda, May 1-5, 2023},
publisher = {OpenReview.net},
year = {2023},
url = {https://openreview.net/pdf?id=9kBCMNb5mc},
timestamp = {Wed, 27 Dec 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/iclr/Zheng0QFYSW23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/Amortila0S23,
author = {Philip Amortila and
Nan Jiang and
Csaba Szepesv{\'{a}}ri},
editor = {Andreas Krause and
Emma Brunskill and
Kyunghyun Cho and
Barbara Engelhardt and
Sivan Sabato and
Jonathan Scarlett},
title = {The Optimal Approximation Factors in Misspecified Off-Policy Value
Function Estimation},
booktitle = {International Conference on Machine Learning, {ICML} 2023, 23-29 July
2023, Honolulu, Hawaii, {USA}},
series = {Proceedings of Machine Learning Research},
volume = {202},
pages = {768--790},
publisher = {{PMLR}},
year = {2023},
url = {https://proceedings.mlr.press/v202/amortila23a.html},
timestamp = {Mon, 28 Aug 2023 17:23:08 +0200},
biburl = {https://dblp.org/rec/conf/icml/Amortila0S23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/KitamuraKTVVYMM23,
author = {Toshinori Kitamura and
Tadashi Kozuno and
Yunhao Tang and
Nino Vieillard and
Michal Valko and
Wenhao Yang and
Jincheng Mei and
Pierre M{\'{e}}nard and
Mohammad Gheshlaghi Azar and
R{\'{e}}mi Munos and
Olivier Pietquin and
Matthieu Geist and
Csaba Szepesv{\'{a}}ri and
Wataru Kumagai and
Yutaka Matsuo},
editor = {Andreas Krause and
Emma Brunskill and
Kyunghyun Cho and
Barbara Engelhardt and
Sivan Sabato and
Jonathan Scarlett},
title = {Regularization and Variance-Weighted Regression Achieves Minimax Optimality
in Linear MDPs: Theory and Practice},
booktitle = {International Conference on Machine Learning, {ICML} 2023, 23-29 July
2023, Honolulu, Hawaii, {USA}},
series = {Proceedings of Machine Learning Research},
volume = {202},
pages = {17135--17175},
publisher = {{PMLR}},
year = {2023},
url = {https://proceedings.mlr.press/v202/kitamura23a.html},
timestamp = {Mon, 28 Aug 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/KitamuraKTVVYMM23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/MeiZ0ASS23,
author = {Jincheng Mei and
Zixin Zhong and
Bo Dai and
Alekh Agarwal and
Csaba Szepesv{\'{a}}ri and
Dale Schuurmans},
editor = {Andreas Krause and
Emma Brunskill and
Kyunghyun Cho and
Barbara Engelhardt and
Sivan Sabato and
Jonathan Scarlett},
title = {Stochastic Gradient Succeeds for Bandits},
booktitle = {International Conference on Machine Learning, {ICML} 2023, 23-29 July
2023, Honolulu, Hawaii, {USA}},
series = {Proceedings of Machine Learning Research},
volume = {202},
pages = {24325--24360},
publisher = {{PMLR}},
year = {2023},
url = {https://proceedings.mlr.press/v202/mei23a.html},
timestamp = {Mon, 28 Aug 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/MeiZ0ASS23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/ZhaoSSJ23,
author = {Yao Zhao and
Connor Stephens and
Csaba Szepesv{\'{a}}ri and
Kwang{-}Sung Jun},
editor = {Andreas Krause and
Emma Brunskill and
Kyunghyun Cho and
Barbara Engelhardt and
Sivan Sabato and
Jonathan Scarlett},
title = {Revisiting Simple Regret: Fast Rates for Returning a Good Arm},
booktitle = {International Conference on Machine Learning, {ICML} 2023, 23-29 July
2023, Honolulu, Hawaii, {USA}},
series = {Proceedings of Machine Learning Research},
volume = {202},
pages = {42110--42158},
publisher = {{PMLR}},
year = {2023},
url = {https://proceedings.mlr.press/v202/zhao23g.html},
timestamp = {Mon, 28 Aug 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/ZhaoSSJ23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/KirschnerBCTS23,
author = {Johannes Kirschner and
Seyed Alireza Bakhtiari and
Kushagra Chandak and
Volodymyr Tkachuk and
Csaba Szepesv{\'{a}}ri},
editor = {Alice Oh and
Tristan Naumann and
Amir Globerson and
Kate Saenko and
Moritz Hardt and
Sergey Levine},
title = {Regret Minimization via Saddle Point Optimization},
booktitle = {Advances in Neural Information Processing Systems 36: Annual Conference
on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans,
LA, USA, December 10 - 16, 2023},
year = {2023},
url = {http://papers.nips.cc/paper\_files/paper/2023/hash/6eaf8c729af4fbeb18006dc2e6a41d9b-Abstract-Conference.html},
timestamp = {Fri, 01 Mar 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/KirschnerBCTS23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/LeeLAJLS23,
author = {Chung{-}Wei Lee and
Qinghua Liu and
Yasin Abbasi{-}Yadkori and
Chi Jin and
Tor Lattimore and
Csaba Szepesv{\'{a}}ri},
editor = {Alice Oh and
Tristan Naumann and
Amir Globerson and
Kate Saenko and
Moritz Hardt and
Sergey Levine},
title = {Context-lumpable stochastic bandits},
booktitle = {Advances in Neural Information Processing Systems 36: Annual Conference
on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans,
LA, USA, December 10 - 16, 2023},
year = {2023},
url = {http://papers.nips.cc/paper\_files/paper/2023/hash/f564a952c1b86684baf7d7241ae27ac8-Abstract-Conference.html},
timestamp = {Fri, 01 Mar 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/LeeLAJLS23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/LiuW00S23,
author = {Qinghua Liu and
Gell{\'{e}}rt Weisz and
Andr{\'{a}}s Gy{\"{o}}rgy and
Chi Jin and
Csaba Szepesv{\'{a}}ri},
editor = {Alice Oh and
Tristan Naumann and
Amir Globerson and
Kate Saenko and
Moritz Hardt and
Sergey Levine},
title = {Optimistic Natural Policy Gradient: a Simple Efficient Policy Optimization
Framework for Online {RL}},
booktitle = {Advances in Neural Information Processing Systems 36: Annual Conference
on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans,
LA, USA, December 10 - 16, 2023},
year = {2023},
url = {http://papers.nips.cc/paper\_files/paper/2023/hash/0b13c22ca208bc08f3fd13793292f25f-Abstract-Conference.html},
timestamp = {Fri, 01 Mar 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/LiuW00S23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/Mei0AGSS23,
author = {Jincheng Mei and
Bo Dai and
Alekh Agarwal and
Mohammad Ghavamzadeh and
Csaba Szepesv{\'{a}}ri and
Dale Schuurmans},
editor = {Alice Oh and
Tristan Naumann and
Amir Globerson and
Kate Saenko and
Moritz Hardt and
Sergey Levine},
title = {Ordering-based Conditions for Global Convergence of Policy Gradient
Methods},
booktitle = {Advances in Neural Information Processing Systems 36: Annual Conference
on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans,
LA, USA, December 10 - 16, 2023},
year = {2023},
url = {http://papers.nips.cc/paper\_files/paper/2023/hash/61c00c07e6d27285e4b952e96cc65666-Abstract-Conference.html},
timestamp = {Fri, 01 Mar 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/Mei0AGSS23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/Weisz0S23,
author = {Gell{\'{e}}rt Weisz and
Andr{\'{a}}s Gy{\"{o}}rgy and
Csaba Szepesv{\'{a}}ri},
editor = {Alice Oh and
Tristan Naumann and
Amir Globerson and
Kate Saenko and
Moritz Hardt and
Sergey Levine},
title = {Online {RL} in Linearly q\({}^{\mbox{{\(\pi\)}}}\)-Realizable MDPs
Is as Easy as in Linear MDPs If You Learn What to Ignore},
booktitle = {Advances in Neural Information Processing Systems 36: Annual Conference
on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans,
LA, USA, December 10 - 16, 2023},
year = {2023},
url = {http://papers.nips.cc/paper\_files/paper/2023/hash/b973a107336177a274069cefb011244c-Abstract-Conference.html},
timestamp = {Fri, 01 Mar 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/Weisz0S23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/stoc/LiuNS023,
author = {Qinghua Liu and
Praneeth Netrapalli and
Csaba Szepesv{\'{a}}ri and
Chi Jin},
editor = {Barna Saha and
Rocco A. Servedio},
title = {Optimistic {MLE:} {A} Generic Model-Based Algorithm for Partially
Observable Sequential Decision Making},
booktitle = {Proceedings of the 55th Annual {ACM} Symposium on Theory of Computing,
{STOC} 2023, Orlando, FL, USA, June 20-23, 2023},
pages = {363--376},
publisher = {{ACM}},
year = {2023},
url = {https://doi.org/10.1145/3564246.3585161},
doi = {10.1145/3564246.3585161},
timestamp = {Mon, 22 May 2023 13:01:48 +0200},
biburl = {https://dblp.org/rec/conf/stoc/LiuNS023.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2301-06276,
author = {Jincheng Mei and
Wesley Chung and
Valentin Thomas and
Bo Dai and
Csaba Szepesv{\'{a}}ri and
Dale Schuurmans},
title = {The Role of Baselines in Policy Gradient Optimization},
journal = {CoRR},
volume = {abs/2301.06276},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2301.06276},
doi = {10.48550/ARXIV.2301.06276},
eprinttype = {arXiv},
eprint = {2301.06276},
timestamp = {Thu, 29 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2301-06276.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2301-12579,
author = {Dong Yin and
Sridhar Thiagarajan and
Nevena Lazic and
Nived Rajaraman and
Botao Hao and
Csaba Szepesv{\'{a}}ri},
title = {Sample Efficient Deep Reinforcement Learning via Local Planning},
journal = {CoRR},
volume = {abs/2301.12579},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2301.12579},
doi = {10.48550/ARXIV.2301.12579},
eprinttype = {arXiv},
eprint = {2301.12579},
timestamp = {Wed, 01 Feb 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2301-12579.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2302-04376,
author = {Volodymyr Tkachuk and
Seyed Alireza Bakhtiari and
Johannes Kirschner and
Matej Jusup and
Ilija Bogunovic and
Csaba Szepesv{\'{a}}ri},
title = {Efficient Planning in Combinatorial Action Spaces with Applications
to Cooperative Multi-Agent Reinforcement Learning},
journal = {CoRR},
volume = {abs/2302.04376},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2302.04376},
doi = {10.48550/ARXIV.2302.04376},
eprinttype = {arXiv},
eprint = {2302.04376},
timestamp = {Mon, 13 Feb 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2302-04376.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2302-12940,
author = {Daniel Kane and
Sihan Liu and
Shachar Lovett and
Gaurav Mahajan and
Csaba Szepesv{\'{a}}ri and
Gell{\'{e}}rt Weisz},
title = {Exponential Hardness of Reinforcement Learning with Linear Function
Approximation},
journal = {CoRR},
volume = {abs/2302.12940},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2302.12940},
doi = {10.48550/ARXIV.2302.12940},
eprinttype = {arXiv},
eprint = {2302.12940},
timestamp = {Tue, 09 Apr 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2302-12940.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2305-11032,
author = {Qinghua Liu and
Gell{\'{e}}rt Weisz and
Andr{\'{a}}s Gy{\"{o}}rgy and
Chi Jin and
Csaba Szepesv{\'{a}}ri},
title = {Optimistic Natural Policy Gradient: a Simple Efficient Policy Optimization
Framework for Online {RL}},
journal = {CoRR},
volume = {abs/2305.11032},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2305.11032},
doi = {10.48550/ARXIV.2305.11032},
eprinttype = {arXiv},
eprint = {2305.11032},
timestamp = {Thu, 25 May 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2305-11032.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2305-13185,
author = {Toshinori Kitamura and
Tadashi Kozuno and
Yunhao Tang and
Nino Vieillard and
Michal Valko and
Wenhao Yang and
Jincheng Mei and
Pierre M{\'{e}}nard and
Mohammad Gheshlaghi Azar and
R{\'{e}}mi Munos and
Olivier Pietquin and
Matthieu Geist and
Csaba Szepesv{\'{a}}ri and
Wataru Kumagai and
Yutaka Matsuo},
title = {Regularization and Variance-Weighted Regression Achieves Minimax Optimality
in Linear MDPs: Theory and Practice},
journal = {CoRR},
volume = {abs/2305.13185},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2305.13185},
doi = {10.48550/ARXIV.2305.13185},
eprinttype = {arXiv},
eprint = {2305.13185},
timestamp = {Fri, 26 May 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2305-13185.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2306-13053,
author = {Chung{-}Wei Lee and
Qinghua Liu and
Yasin Abbasi{-}Yadkori and
Chi Jin and
Tor Lattimore and
Csaba Szepesv{\'{a}}ri},
title = {Context-lumpable stochastic bandits},
journal = {CoRR},
volume = {abs/2306.13053},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2306.13053},
doi = {10.48550/ARXIV.2306.13053},
eprinttype = {arXiv},
eprint = {2306.13053},
timestamp = {Tue, 27 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2306-13053.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2307-13332,
author = {Philip Amortila and
Nan Jiang and
Csaba Szepesv{\'{a}}ri},
title = {The Optimal Approximation Factors in Misspecified Off-Policy Value
Function Estimation},
journal = {CoRR},
volume = {abs/2307.13332},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2307.13332},
doi = {10.48550/ARXIV.2307.13332},
eprinttype = {arXiv},
eprint = {2307.13332},
timestamp = {Tue, 01 Aug 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2307-13332.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2310-07811,
author = {Gell{\'{e}}rt Weisz and
Andr{\'{a}}s Gy{\"{o}}rgy and
Csaba Szepesv{\'{a}}ri},
title = {Online {RL} in Linearly q\({}^{\mbox{{\(\pi\)}}}\)-Realizable MDPs
Is as Easy as in Linear MDPs If You Learn What to Ignore},
journal = {CoRR},
volume = {abs/2310.07811},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2310.07811},
doi = {10.48550/ARXIV.2310.07811},
eprinttype = {arXiv},
eprint = {2310.07811},
timestamp = {Tue, 24 Oct 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2310-07811.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2310-20581,
author = {Jihao Andreas Lin and
Shreyas Padhy and
Javier Antor{\'{a}}n and
Austin Tripp and
Alexander Terenin and
Csaba Szepesv{\'{a}}ri and
Jos{\'{e}} Miguel Hern{\'{a}}ndez{-}Lobato and
David Janz},
title = {Stochastic Gradient Descent for Gaussian Processes Done Right},
journal = {CoRR},
volume = {abs/2310.20581},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2310.20581},
doi = {10.48550/ARXIV.2310.20581},
eprinttype = {arXiv},
eprint = {2310.20581},
timestamp = {Fri, 03 Nov 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2310-20581.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2311-07565,
author = {David Janz and
Shuai Liu and
Alex Ayoub and
Csaba Szepesv{\'{a}}ri},
title = {Exploration via linearly perturbed loss minimisation},
journal = {CoRR},
volume = {abs/2311.07565},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2311.07565},
doi = {10.48550/ARXIV.2311.07565},
eprinttype = {arXiv},
eprint = {2311.07565},
timestamp = {Wed, 15 Nov 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2311-07565.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2311-08376,
author = {David Janz and
Alexander E. Litvak and
Csaba Szepesv{\'{a}}ri},
title = {Ensemble sampling for linear bandits: small ensembles suffice},
journal = {CoRR},
volume = {abs/2311.08376},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2311.08376},
doi = {10.48550/ARXIV.2311.08376},
eprinttype = {arXiv},
eprint = {2311.08376},
timestamp = {Thu, 23 Nov 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2311-08376.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aistats/HaoLYAS22,
author = {Botao Hao and
Nevena Lazic and
Dong Yin and
Yasin Abbasi{-}Yadkori and
Csaba Szepesv{\'{a}}ri},
editor = {Gustau Camps{-}Valls and
Francisco J. R. Ruiz and
Isabel Valera},
title = {Confident Least Square Value Iteration with Local Access to a Simulator},
booktitle = {International Conference on Artificial Intelligence and Statistics,
{AISTATS} 2022, 28-30 March 2022, Virtual Event},
series = {Proceedings of Machine Learning Research},
volume = {151},
pages = {2420--2435},
publisher = {{PMLR}},
year = {2022},
url = {https://proceedings.mlr.press/v151/hao22a.html},
timestamp = {Sat, 30 Sep 2023 09:34:08 +0200},
biburl = {https://dblp.org/rec/conf/aistats/HaoLYAS22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aistats/RajJ0S22,
author = {Anant Raj and
Pooria Joulani and
Andr{\'{a}}s Gy{\"{o}}rgy and
Csaba Szepesv{\'{a}}ri},
editor = {Gustau Camps{-}Valls and
Francisco J. R. Ruiz and
Isabel Valera},
title = {Faster Rates, Adaptive Algorithms, and Finite-Time Bounds for Linear
Composition Optimization and Gradient {TD} Learning},
booktitle = {International Conference on Artificial Intelligence and Statistics,
{AISTATS} 2022, 28-30 March 2022, Virtual Event},
series = {Proceedings of Machine Learning Research},
volume = {151},
pages = {7176--7186},
publisher = {{PMLR}},
year = {2022},
url = {https://proceedings.mlr.press/v151/raj22a.html},
timestamp = {Fri, 20 May 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/aistats/RajJ0S22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aistats/XiaoLDSS22,
author = {Chenjun Xiao and
Ilbin Lee and
Bo Dai and
Dale Schuurmans and
Csaba Szepesv{\'{a}}ri},
editor = {Gustau Camps{-}Valls and
Francisco J. R. Ruiz and
Isabel Valera},
title = {The Curse of Passive Data Collection in Batch Reinforcement Learning},
booktitle = {International Conference on Artificial Intelligence and Statistics,
{AISTATS} 2022, 28-30 March 2022, Virtual Event},
series = {Proceedings of Machine Learning Research},
volume = {151},
pages = {8413--8438},
publisher = {{PMLR}},
year = {2022},
url = {https://proceedings.mlr.press/v151/xiao22b.html},
timestamp = {Thu, 29 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/aistats/XiaoLDSS22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/alt/WeiszS022,
author = {Gell{\'{e}}rt Weisz and
Csaba Szepesv{\'{a}}ri and
Andr{\'{a}}s Gy{\"{o}}rgy},
editor = {Sanjoy Dasgupta and
Nika Haghtalab},
title = {TensorPlan and the Few Actions Lower Bound for Planning in MDPs under
Linear Realizability of Optimal Value Functions},
booktitle = {International Conference on Algorithmic Learning Theory, 29 March
- 1 April 2022, Paris, France},
series = {Proceedings of Machine Learning Research},
volume = {167},
pages = {1097--1137},
publisher = {{PMLR}},
year = {2022},
url = {https://proceedings.mlr.press/v167/weisz22a.html},
timestamp = {Fri, 10 Mar 2023 11:41:45 +0100},
biburl = {https://dblp.org/rec/conf/alt/WeiszS022.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/alt/YinHALS22,
author = {Dong Yin and
Botao Hao and
Yasin Abbasi{-}Yadkori and
Nevena Lazic and
Csaba Szepesv{\'{a}}ri},
editor = {Sanjoy Dasgupta and
Nika Haghtalab},
title = {Efficient local planning with linear function approximation},
booktitle = {International Conference on Algorithmic Learning Theory, 29 March
- 1 April 2022, Paris, France},
series = {Proceedings of Machine Learning Research},
volume = {167},
pages = {1165--1192},
publisher = {{PMLR}},
year = {2022},
url = {https://proceedings.mlr.press/v167/yin22a.html},
timestamp = {Fri, 25 Mar 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/alt/YinHALS22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/colt/LiuCSJ22,
author = {Qinghua Liu and
Alan Chung and
Csaba Szepesv{\'{a}}ri and
Chi Jin},
editor = {Po{-}Ling Loh and
Maxim Raginsky},
title = {When Is Partially Observable Reinforcement Learning Not Scary?},
booktitle = {Conference on Learning Theory, 2-5 July 2022, London, {UK}},
series = {Proceedings of Machine Learning Research},
volume = {178},
pages = {5175--5220},
publisher = {{PMLR}},
year = {2022},
url = {https://proceedings.mlr.press/v178/liu22f.html},
timestamp = {Wed, 07 Dec 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/colt/LiuCSJ22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/LiuS022,
author = {Qinghua Liu and
Csaba Szepesv{\'{a}}ri and
Chi Jin},
editor = {Sanmi Koyejo and
S. Mohamed and
A. Agarwal and
Danielle Belgrave and
K. Cho and
A. Oh},
title = {Sample-Efficient Reinforcement Learning of Partially Observable Markov
Games},
booktitle = {Advances in Neural Information Processing Systems 35: Annual Conference
on Neural Information Processing Systems 2022, NeurIPS 2022, New Orleans,
LA, USA, November 28 - December 9, 2022},
year = {2022},
url = {http://papers.nips.cc/paper\_files/paper/2022/hash/743459dae9b2c5d2904e5432d5298128-Abstract-Conference.html},
timestamp = {Mon, 08 Jan 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/LiuS022.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/MeiCTDSS22,
author = {Jincheng Mei and
Wesley Chung and
Valentin Thomas and
Bo Dai and
Csaba Szepesv{\'{a}}ri and
Dale Schuurmans},
editor = {Sanmi Koyejo and
S. Mohamed and
A. Agarwal and
Danielle Belgrave and
K. Cho and
A. Oh},
title = {The Role of Baselines in Policy Gradient Optimization},
booktitle = {Advances in Neural Information Processing Systems 35: Annual Conference
on Neural Information Processing Systems 2022, NeurIPS 2022, New Orleans,
LA, USA, November 28 - December 9, 2022},
year = {2022},
url = {http://papers.nips.cc/paper\_files/paper/2022/hash/718d02a76d69686a36eccc8cde3e6a41-Abstract-Conference.html},
timestamp = {Mon, 08 Jan 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/MeiCTDSS22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/Vaswani0S22,
author = {Sharan Vaswani and
Lin Yang and
Csaba Szepesv{\'{a}}ri},
editor = {Sanmi Koyejo and
S. Mohamed and
A. Agarwal and
Danielle Belgrave and
K. Cho and
A. Oh},
title = {Near-Optimal Sample Complexity Bounds for Constrained MDPs},
booktitle = {Advances in Neural Information Processing Systems 35: Annual Conference
on Neural Information Processing Systems 2022, NeurIPS 2022, New Orleans,
LA, USA, November 28 - December 9, 2022},
year = {2022},
url = {http://papers.nips.cc/paper\_files/paper/2022/hash/14a5ebc9cd2e507cd811df78c15bf5d7-Abstract-Conference.html},
timestamp = {Mon, 08 Jan 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/Vaswani0S22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/Weisz0KS22,
author = {Gell{\'{e}}rt Weisz and
Andr{\'{a}}s Gy{\"{o}}rgy and
Tadashi Kozuno and
Csaba Szepesv{\'{a}}ri},
editor = {Sanmi Koyejo and
S. Mohamed and
A. Agarwal and
Danielle Belgrave and
K. Cho and
A. Oh},
title = {Confident Approximate Policy Iteration for Efficient Local Planning
in {\textdollar}q{\^{}}{\textbackslash}pi{\textdollar}-realizable
MDPs},
booktitle = {Advances in Neural Information Processing Systems 35: Annual Conference
on Neural Information Processing Systems 2022, NeurIPS 2022, New Orleans,
LA, USA, November 28 - December 9, 2022},
year = {2022},
url = {http://papers.nips.cc/paper\_files/paper/2022/hash/a3bfb116214815682a0d0d88ea95cd12-Abstract-Conference.html},
timestamp = {Mon, 08 Jan 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/Weisz0KS22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/YuanNWZCSW22,
author = {Hui Yuan and
Chengzhuo Ni and
Huazheng Wang and
Xuezhou Zhang and
Le Cong and
Csaba Szepesv{\'{a}}ri and
Mengdi Wang},
editor = {Sanmi Koyejo and
S. Mohamed and
A. Agarwal and
Danielle Belgrave and
K. Cho and
A. Oh},
title = {Bandit Theory and Thompson Sampling-Guided Directed Evolution for
Sequence Optimization},
booktitle = {Advances in Neural Information Processing Systems 35: Annual Conference
on Neural Information Processing Systems 2022, NeurIPS 2022, New Orleans,
LA, USA, November 28 - December 9, 2022},
year = {2022},
url = {http://papers.nips.cc/paper\_files/paper/2022/hash/fa3c139cf8084de7bfd944f1c90c8695-Abstract-Conference.html},
timestamp = {Mon, 08 Jan 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/YuanNWZCSW22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/uai/RenZSD22,
author = {Tongzheng Ren and
Tianjun Zhang and
Csaba Szepesv{\'{a}}ri and
Bo Dai},
editor = {James Cussens and
Kun Zhang},
title = {A free lunch from the noise: Provable and practical exploration for
representation learning},
booktitle = {Uncertainty in Artificial Intelligence, Proceedings of the Thirty-Eighth
Conference on Uncertainty in Artificial Intelligence, {UAI} 2022,
1-5 August 2022, Eindhoven, The Netherlands},
series = {Proceedings of Machine Learning Research},
volume = {180},
pages = {1686--1696},
publisher = {{PMLR}},
year = {2022},
url = {https://proceedings.mlr.press/v180/ren22a.html},
timestamp = {Mon, 03 Jul 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/uai/RenZSD22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@proceedings{DBLP:conf/icml/2022,
editor = {Kamalika Chaudhuri and
Stefanie Jegelka and
Le Song and
Csaba Szepesv{\'{a}}ri and
Gang Niu and
Sivan Sabato},
title = {International Conference on Machine Learning, {ICML} 2022, 17-23 July
2022, Baltimore, Maryland, {USA}},
series = {Proceedings of Machine Learning Research},
volume = {162},
publisher = {{PMLR}},
year = {2022},
url = {http://proceedings.mlr.press/v162/},
timestamp = {Tue, 12 Jul 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/2022.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2204-05176,
author = {Arushi Jain and
Sharan Vaswani and
Reza Babanezhad and
Csaba Szepesv{\'{a}}ri and
Doina Precup},
title = {Towards Painless Policy Optimization for Constrained MDPs},
journal = {CoRR},
volume = {abs/2204.05176},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2204.05176},
doi = {10.48550/ARXIV.2204.05176},
eprinttype = {arXiv},
eprint = {2204.05176},
timestamp = {Wed, 07 Dec 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2204-05176.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2204-08967,
author = {Qinghua Liu and
Alan Chung and
Csaba Szepesv{\'{a}}ri and
Chi Jin},
title = {When Is Partially Observable Reinforcement Learning Not Scary?},
journal = {CoRR},
volume = {abs/2204.08967},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2204.08967},
doi = {10.48550/ARXIV.2204.08967},
eprinttype = {arXiv},
eprint = {2204.08967},
timestamp = {Wed, 07 Dec 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2204-08967.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2205-14211,
author = {Tadashi Kozuno and
Wenhao Yang and
Nino Vieillard and
Toshinori Kitamura and
Yunhao Tang and
Jincheng Mei and
Pierre M{\'{e}}nard and
Mohammad Gheshlaghi Azar and
Michal Valko and
R{\'{e}}mi Munos and
Olivier Pietquin and
Matthieu Geist and
Csaba Szepesv{\'{a}}ri},
title = {KL-Entropy-Regularized {RL} with a Generative Model is Minimax Optimal},
journal = {CoRR},
volume = {abs/2205.14211},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2205.14211},
doi = {10.48550/ARXIV.2205.14211},
eprinttype = {arXiv},
eprint = {2205.14211},
timestamp = {Wed, 01 Jun 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2205-14211.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2206-01315,
author = {Qinghua Liu and
Csaba Szepesv{\'{a}}ri and
Chi Jin},
title = {Sample-Efficient Reinforcement Learning of Partially Observable Markov
Games},
journal = {CoRR},
volume = {abs/2206.01315},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2206.01315},
doi = {10.48550/ARXIV.2206.01315},
eprinttype = {arXiv},
eprint = {2206.01315},
timestamp = {Wed, 07 Dec 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2206-01315.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2206-02092,
author = {Hui Yuan and
Chengzhuo Ni and
Huazheng Wang and
Xuezhou Zhang and
Le Cong and
Csaba Szepesv{\'{a}}ri and
Mengdi Wang},
title = {Bandit Theory and Thompson Sampling-Guided Directed Evolution for
Sequence Optimization},
journal = {CoRR},
volume = {abs/2206.02092},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2206.02092},
doi = {10.48550/ARXIV.2206.02092},
eprinttype = {arXiv},
eprint = {2206.02092},
timestamp = {Sat, 30 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2206-02092.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2206-06270,
author = {Sharan Vaswani and
Lin F. Yang and
Csaba Szepesv{\'{a}}ri},
title = {Near-Optimal Sample Complexity Bounds for Constrained MDPs},
journal = {CoRR},
volume = {abs/2206.06270},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2206.06270},
doi = {10.48550/ARXIV.2206.06270},
eprinttype = {arXiv},
eprint = {2206.06270},
timestamp = {Sat, 30 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2206-06270.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2209-14997,
author = {Qinghua Liu and
Praneeth Netrapalli and
Csaba Szepesv{\'{a}}ri and
Chi Jin},
title = {Optimistic {MLE} - {A} Generic Model-based Algorithm for Partially
Observable Sequential Decision Making},
journal = {CoRR},
volume = {abs/2209.14997},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2209.14997},
doi = {10.48550/ARXIV.2209.14997},
eprinttype = {arXiv},
eprint = {2209.14997},
timestamp = {Wed, 07 Dec 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2209-14997.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2210-15755,
author = {Gell{\'{e}}rt Weisz and
Andr{\'{a}}s Gy{\"{o}}rgy and
Tadashi Kozuno and
Csaba Szepesv{\'{a}}ri},
title = {Confident Approximate Policy Iteration for Efficient Local Planning
in q\({}^{\mbox{{\(\pi\)}}}\)-realizable MDPs},
journal = {CoRR},
volume = {abs/2210.15755},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2210.15755},
doi = {10.48550/ARXIV.2210.15755},
eprinttype = {arXiv},
eprint = {2210.15755},
timestamp = {Wed, 02 Nov 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2210-15755.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2210-16913,
author = {Yao Zhao and
Connor Stephens and
Csaba Szepesv{\'{a}}ri and
Kwang{-}Sung Jun},
title = {Revisiting Simple Regret Minimization in Multi-Armed Bandits},
journal = {CoRR},
volume = {abs/2210.16913},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2210.16913},
doi = {10.48550/ARXIV.2210.16913},
eprinttype = {arXiv},
eprint = {2210.16913},
timestamp = {Wed, 02 Nov 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2210-16913.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2212-13848,
author = {Ilja Kuzborskij and
Csaba Szepesv{\'{a}}ri},
title = {Learning Lipschitz Functions by GD-trained Shallow Overparameterized
ReLU Neural Networks},
journal = {CoRR},
volume = {abs/2212.13848},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2212.13848},
doi = {10.48550/ARXIV.2212.13848},
eprinttype = {arXiv},
eprint = {2212.13848},
timestamp = {Thu, 05 Jan 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2212-13848.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/jmlr/Perez-OrtizRSS21,
author = {Mar{\'{\i}}a P{\'{e}}rez{-}Ortiz and
Omar Rivasplata and
John Shawe{-}Taylor and
Csaba Szepesv{\'{a}}ri},
title = {Tighter Risk Certificates for Neural Networks},
journal = {J. Mach. Learn. Res.},
volume = {22},
pages = {227:1--227:40},
year = {2021},
url = {http://jmlr.org/papers/v22/20-879.html},
timestamp = {Mon, 04 Jul 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/jmlr/Perez-OrtizRSS21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ml/LiGLSW21,
author = {Yuxi Li and
Alborz Geramifard and
Lihong Li and
Csaba Szepesv{\'{a}}ri and
Tao Wang},
title = {Guest editorial: special issue on reinforcement learning for real
life},
journal = {Mach. Learn.},
volume = {110},
number = {9},
pages = {2291--2293},
year = {2021},
url = {https://doi.org/10.1007/s10994-021-06041-3},
doi = {10.1007/S10994-021-06041-3},
timestamp = {Tue, 30 Aug 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/ml/LiGLSW21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aistats/HaoLSW21,
author = {Botao Hao and
Tor Lattimore and
Csaba Szepesv{\'{a}}ri and
Mengdi Wang},
editor = {Arindam Banerjee and
Kenji Fukumizu},
title = {Online Sparse Reinforcement Learning},
booktitle = {The 24th International Conference on Artificial Intelligence and Statistics,
{AISTATS} 2021, April 13-15, 2021, Virtual Event},
series = {Proceedings of Machine Learning Research},
volume = {130},
pages = {316--324},
publisher = {{PMLR}},
year = {2021},
url = {http://proceedings.mlr.press/v130/hao21a.html},
timestamp = {Wed, 14 Apr 2021 16:51:37 +0200},
biburl = {https://dblp.org/rec/conf/aistats/HaoLSW21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aistats/HaoLAJS21,
author = {Botao Hao and
Nevena Lazic and
Yasin Abbasi{-}Yadkori and
Pooria Joulani and
Csaba Szepesv{\'{a}}ri},
editor = {Arindam Banerjee and
Kenji Fukumizu},
title = {Adaptive Approximate Policy Iteration},
booktitle = {The 24th International Conference on Artificial Intelligence and Statistics,
{AISTATS} 2021, April 13-15, 2021, Virtual Event},
series = {Proceedings of Machine Learning Research},
volume = {130},
pages = {523--531},
publisher = {{PMLR}},
year = {2021},
url = {http://proceedings.mlr.press/v130/hao21b.html},
timestamp = {Wed, 14 Apr 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/aistats/HaoLAJS21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aistats/KuzborskijV0S21,
author = {Ilja Kuzborskij and
Claire Vernade and
Andr{\'{a}}s Gy{\"{o}}rgy and
Csaba Szepesv{\'{a}}ri},
editor = {Arindam Banerjee and
Kenji Fukumizu},
title = {Confident Off-Policy Evaluation and Selection through Self-Normalized
Importance Weighting},
booktitle = {The 24th International Conference on Artificial Intelligence and Statistics,
{AISTATS} 2021, April 13-15, 2021, Virtual Event},
series = {Proceedings of Machine Learning Research},
volume = {130},
pages = {640--648},
publisher = {{PMLR}},
year = {2021},
url = {http://proceedings.mlr.press/v130/kuzborskij21a.html},
timestamp = {Wed, 14 Apr 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/aistats/KuzborskijV0S21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/alt/WeiszAS21,
author = {Gell{\'{e}}rt Weisz and
Philip Amortila and
Csaba Szepesv{\'{a}}ri},
editor = {Vitaly Feldman and
Katrina Ligett and
Sivan Sabato},
title = {Exponential Lower Bounds for Planning in MDPs With Linearly-Realizable
Optimal Action-Value Functions},
booktitle = {Algorithmic Learning Theory, 16-19 March 2021, Virtual Conference,
Worldwide},
series = {Proceedings of Machine Learning Research},
volume = {132},
pages = {1237--1264},
publisher = {{PMLR}},
year = {2021},
url = {http://proceedings.mlr.press/v132/weisz21a.html},
timestamp = {Fri, 26 Mar 2021 15:45:50 +0100},
biburl = {https://dblp.org/rec/conf/alt/WeiszAS21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/colt/KirschnerLVS21,
author = {Johannes Kirschner and
Tor Lattimore and
Claire Vernade and
Csaba Szepesv{\'{a}}ri},
editor = {Mikhail Belkin and
Samory Kpotufe},
title = {Asymptotically Optimal Information-Directed Sampling},
booktitle = {Conference on Learning Theory, {COLT} 2021, 15-19 August 2021, Boulder,
Colorado, {USA}},
series = {Proceedings of Machine Learning Research},
volume = {134},
pages = {2777--2821},
publisher = {{PMLR}},
year = {2021},
url = {http://proceedings.mlr.press/v134/kirschner21a.html},
timestamp = {Wed, 25 Aug 2021 17:11:16 +0200},
biburl = {https://dblp.org/rec/conf/colt/KirschnerLVS21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/colt/KuzborskijS21,
author = {Ilja Kuzborskij and
Csaba Szepesv{\'{a}}ri},
editor = {Mikhail Belkin and
Samory Kpotufe},
title = {Nonparametric Regression with Shallow Overparameterized Neural Networks
Trained by {GD} with Early Stopping},
booktitle = {Conference on Learning Theory, {COLT} 2021, 15-19 August 2021, Boulder,
Colorado, {USA}},
series = {Proceedings of Machine Learning Research},
volume = {134},
pages = {2853--2890},
publisher = {{PMLR}},
year = {2021},
url = {http://proceedings.mlr.press/v134/kuzborskij21a.html},
timestamp = {Wed, 25 Aug 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/colt/KuzborskijS21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/colt/WeiszAJAJS21,
author = {Gell{\'{e}}rt Weisz and
Philip Amortila and
Barnab{\'{a}}s Janzer and
Yasin Abbasi{-}Yadkori and
Nan Jiang and
Csaba Szepesv{\'{a}}ri},
editor = {Mikhail Belkin and
Samory Kpotufe},
title = {On Query-efficient Planning in MDPs under Linear Realizability of
the Optimal State-value Function},
booktitle = {Conference on Learning Theory, {COLT} 2021, 15-19 August 2021, Boulder,
Colorado, {USA}},
series = {Proceedings of Machine Learning Research},
volume = {134},
pages = {4355--4385},
publisher = {{PMLR}},
year = {2021},
url = {http://proceedings.mlr.press/v134/weisz21a.html},
timestamp = {Tue, 19 Jul 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/colt/WeiszAJAJS21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/colt/ZhouGS21,
author = {Dongruo Zhou and
Quanquan Gu and
Csaba Szepesv{\'{a}}ri},
editor = {Mikhail Belkin and
Samory Kpotufe},
title = {Nearly Minimax Optimal Reinforcement Learning for Linear Mixture Markov
Decision Processes},
booktitle = {Conference on Learning Theory, {COLT} 2021, 15-19 August 2021, Boulder,
Colorado, {USA}},
series = {Proceedings of Machine Learning Research},
volume = {134},
pages = {4532--4576},
publisher = {{PMLR}},
year = {2021},
url = {http://proceedings.mlr.press/v134/zhou21a.html},
timestamp = {Wed, 25 Aug 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/colt/ZhouGS21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/HaoDLSW21,
author = {Botao Hao and
Yaqi Duan and
Tor Lattimore and
Csaba Szepesv{\'{a}}ri and
Mengdi Wang},
editor = {Marina Meila and
Tong Zhang},
title = {Sparse Feature Selection Makes Batch Reinforcement Learning More Sample
Efficient},
booktitle = {Proceedings of the 38th International Conference on Machine Learning,
{ICML} 2021, 18-24 July 2021, Virtual Event},
series = {Proceedings of Machine Learning Research},
volume = {139},
pages = {4063--4073},
publisher = {{PMLR}},
year = {2021},
url = {http://proceedings.mlr.press/v139/hao21a.html},
timestamp = {Wed, 25 Aug 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/HaoDLSW21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/HaoJDLSW21,
author = {Botao Hao and
Xiang Ji and
Yaqi Duan and
Hao Lu and
Csaba Szepesv{\'{a}}ri and
Mengdi Wang},
editor = {Marina Meila and
Tong Zhang},
title = {Bootstrapping Fitted Q-Evaluation for Off-Policy Inference},
booktitle = {Proceedings of the 38th International Conference on Machine Learning,
{ICML} 2021, 18-24 July 2021, Virtual Event},
series = {Proceedings of Machine Learning Research},
volume = {139},
pages = {4074--4084},
publisher = {{PMLR}},
year = {2021},
url = {http://proceedings.mlr.press/v139/hao21b.html},
timestamp = {Wed, 25 Aug 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/HaoJDLSW21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/KonobeevKS21,
author = {Mikhail Konobeev and
Ilja Kuzborskij and
Csaba Szepesv{\'{a}}ri},
editor = {Marina Meila and
Tong Zhang},
title = {A Distribution-dependent Analysis of Meta Learning},
booktitle = {Proceedings of the 38th International Conference on Machine Learning,
{ICML} 2021, 18-24 July 2021, Virtual Event},
series = {Proceedings of Machine Learning Research},
volume = {139},
pages = {5697--5706},
publisher = {{PMLR}},
year = {2021},
url = {http://proceedings.mlr.press/v139/konobeev21a.html},
timestamp = {Wed, 25 Aug 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/KonobeevKS21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/KvetonKZHMBS21,
author = {Branislav Kveton and
Mikhail Konobeev and
Manzil Zaheer and
Chih{-}Wei Hsu and
Martin Mladenov and
Craig Boutilier and
Csaba Szepesv{\'{a}}ri},
editor = {Marina Meila and
Tong Zhang},
title = {Meta-Thompson Sampling},
booktitle = {Proceedings of the 38th International Conference on Machine Learning,
{ICML} 2021, 18-24 July 2021, Virtual Event},
series = {Proceedings of Machine Learning Research},
volume = {139},
pages = {5884--5893},
publisher = {{PMLR}},
year = {2021},
url = {http://proceedings.mlr.press/v139/kveton21a.html},
timestamp = {Wed, 25 Aug 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/KvetonKZHMBS21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/LazicYAS21,
author = {Nevena Lazic and
Dong Yin and
Yasin Abbasi{-}Yadkori and
Csaba Szepesv{\'{a}}ri},
editor = {Marina Meila and
Tong Zhang},
title = {Improved Regret Bound and Experience Replay in Regularized Policy
Iteration},
booktitle = {Proceedings of the 38th International Conference on Machine Learning,
{ICML} 2021, 18-24 July 2021, Virtual Event},
series = {Proceedings of Machine Learning Research},
volume = {139},
pages = {6032--6042},
publisher = {{PMLR}},
year = {2021},
url = {http://proceedings.mlr.press/v139/lazic21a.html},
timestamp = {Wed, 25 Aug 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/LazicYAS21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/MeiGDSS21,
author = {Jincheng Mei and
Yue Gao and
Bo Dai and
Csaba Szepesv{\'{a}}ri and
Dale Schuurmans},
editor = {Marina Meila and
Tong Zhang},
title = {Leveraging Non-uniformity in First-order Non-convex Optimization},
booktitle = {Proceedings of the 38th International Conference on Machine Learning,
{ICML} 2021, 18-24 July 2021, Virtual Event},
series = {Proceedings of Machine Learning Research},
volume = {139},
pages = {7555--7564},
publisher = {{PMLR}},
year = {2021},
url = {http://proceedings.mlr.press/v139/mei21a.html},
timestamp = {Thu, 29 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/MeiGDSS21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/XiaoWMDL0SS21,
author = {Chenjun Xiao and
Yifan Wu and
Jincheng Mei and
Bo Dai and
Tor Lattimore and
Lihong Li and
Csaba Szepesv{\'{a}}ri and
Dale Schuurmans},
editor = {Marina Meila and
Tong Zhang},
title = {On the Optimality of Batch Policy Optimization Algorithms},
booktitle = {Proceedings of the 38th International Conference on Machine Learning,
{ICML} 2021, 18-24 July 2021, Virtual Event},
series = {Proceedings of Machine Learning Research},
volume = {139},
pages = {11362--11371},
publisher = {{PMLR}},
year = {2021},
url = {http://proceedings.mlr.press/v139/xiao21b.html},
timestamp = {Thu, 29 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/XiaoWMDL0SS21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/ZhangNYSW21,
author = {Junyu Zhang and
Chengzhuo Ni and
Zheng Yu and
Csaba Szepesv{\'{a}}ri and
Mengdi Wang},
editor = {Marc'Aurelio Ranzato and
Alina Beygelzimer and
Yann N. Dauphin and
Percy Liang and
Jennifer Wortman Vaughan},
title = {On the Convergence and Sample Efficiency of Variance-Reduced Policy
Gradient Method},
booktitle = {Advances in Neural Information Processing Systems 34: Annual Conference
on Neural Information Processing Systems 2021, NeurIPS 2021, December
6-14, 2021, virtual},
pages = {2228--2240},
year = {2021},
url = {https://proceedings.neurips.cc/paper/2021/hash/11c484ea9305ea4c7bb6b2e6d570d466-Abstract.html},
timestamp = {Tue, 03 May 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/nips/ZhangNYSW21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/MeiDXSS21,
author = {Jincheng Mei and
Bo Dai and
Chenjun Xiao and
Csaba Szepesv{\'{a}}ri and
Dale Schuurmans},
editor = {Marc'Aurelio Ranzato and
Alina Beygelzimer and
Yann N. Dauphin and
Percy Liang and
Jennifer Wortman Vaughan},
title = {Understanding the Effect of Stochasticity in Policy Optimization},
booktitle = {Advances in Neural Information Processing Systems 34: Annual Conference
on Neural Information Processing Systems 2021, NeurIPS 2021, December
6-14, 2021, virtual},
pages = {19339--19351},
year = {2021},
url = {https://proceedings.neurips.cc/paper/2021/hash/a12f69495f41bb3b637ba1b6238884d6-Abstract.html},
timestamp = {Thu, 29 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/nips/MeiDXSS21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/BasuKZS21,
author = {Soumya Basu and
Branislav Kveton and
Manzil Zaheer and
Csaba Szepesv{\'{a}}ri},
editor = {Marc'Aurelio Ranzato and
Alina Beygelzimer and
Yann N. Dauphin and
Percy Liang and
Jennifer Wortman Vaughan},
title = {No Regrets for Learning the Prior in Bandits},
booktitle = {Advances in Neural Information Processing Systems 34: Annual Conference
on Neural Information Processing Systems 2021, NeurIPS 2021, December
6-14, 2021, virtual},
pages = {28029--28041},
year = {2021},
url = {https://proceedings.neurips.cc/paper/2021/hash/ec1f764517b7ffb52057af6df18142b7-Abstract.html},
timestamp = {Tue, 03 May 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/nips/BasuKZS21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/KuzborskijSRRP21,
author = {Ilja Kuzborskij and
Csaba Szepesv{\'{a}}ri and
Omar Rivasplata and
Amal Rannen{-}Triki and
Razvan Pascanu},
editor = {Marc'Aurelio Ranzato and
Alina Beygelzimer and
Yann N. Dauphin and
Percy Liang and
Jennifer Wortman Vaughan},
title = {On the Role of Optimization in Double Descent: {A} Least Squares Study},
booktitle = {Advances in Neural Information Processing Systems 34: Annual Conference
on Neural Information Processing Systems 2021, NeurIPS 2021, December
6-14, 2021, virtual},
pages = {29567--29577},
year = {2021},
url = {https://proceedings.neurips.cc/paper/2021/hash/f754186469a933256d7d64095e963594-Abstract.html},
timestamp = {Tue, 03 May 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/nips/KuzborskijSRRP21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2102-02049,
author = {Gell{\'{e}}rt Weisz and
Philip Amortila and
Barnab{\'{a}}s Janzer and
Yasin Abbasi{-}Yadkori and
Nan Jiang and
Csaba Szepesv{\'{a}}ri},
title = {On Query-efficient Planning in MDPs under Linear Realizability of
the Optimal State-value Function},
journal = {CoRR},
volume = {abs/2102.02049},
year = {2021},
url = {https://arxiv.org/abs/2102.02049},
eprinttype = {arXiv},
eprint = {2102.02049},
timestamp = {Tue, 19 Jul 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2102-02049.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2102-03607,
author = {Botao Hao and
Xiang Ji and
Yaqi Duan and
Hao Lu and
Csaba Szepesv{\'{a}}ri and
Mengdi Wang},
title = {Bootstrapping Statistical Inference for Off-Policy Evaluation},
journal = {CoRR},
volume = {abs/2102.03607},
year = {2021},
url = {https://arxiv.org/abs/2102.03607},
eprinttype = {arXiv},
eprint = {2102.03607},
timestamp = {Wed, 10 Feb 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2102-03607.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2102-06129,
author = {Branislav Kveton and
Mikhail Konobeev and
Manzil Zaheer and
Chih{-}Wei Hsu and
Martin Mladenov and
Craig Boutilier and
Csaba Szepesv{\'{a}}ri},
title = {Meta-Thompson Sampling},
journal = {CoRR},
volume = {abs/2102.06129},
year = {2021},
url = {https://arxiv.org/abs/2102.06129},
eprinttype = {arXiv},
eprint = {2102.06129},
timestamp = {Thu, 18 Feb 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2102-06129.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2102-06234,
author = {Nevena Lazic and
Botao Hao and
Yasin Abbasi{-}Yadkori and
Dale Schuurmans and
Csaba Szepesv{\'{a}}ri},
title = {Optimization Issues in KL-Constrained Approximate Policy Iteration},
journal = {CoRR},
volume = {abs/2102.06234},
year = {2021},
url = {https://arxiv.org/abs/2102.06234},
eprinttype = {arXiv},
eprint = {2102.06234},
timestamp = {Thu, 18 Feb 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2102-06234.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2102-08607,
author = {Junyu Zhang and
Chengzhuo Ni and
Zheng Yu and
Csaba Szepesv{\'{a}}ri and
Mengdi Wang},
title = {On the Convergence and Sample Efficiency of Variance-Reduced Policy
Gradient Method},
journal = {CoRR},
volume = {abs/2102.08607},
year = {2021},
url = {https://arxiv.org/abs/2102.08607},
eprinttype = {arXiv},
eprint = {2102.08607},
timestamp = {Fri, 19 Feb 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2102-08607.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2102-12611,
author = {Nevena Lazic and
Dong Yin and
Yasin Abbasi{-}Yadkori and
Csaba Szepesv{\'{a}}ri},
title = {Improved Regret Bound and Experience Replay in Regularized Policy
Iteration},
journal = {CoRR},
volume = {abs/2102.12611},
year = {2021},
url = {https://arxiv.org/abs/2102.12611},
eprinttype = {arXiv},
eprint = {2102.12611},
timestamp = {Tue, 02 Mar 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2102-12611.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2104-02293,
author = {Chenjun Xiao and
Yifan Wu and
Tor Lattimore and
Bo Dai and
Jincheng Mei and
Lihong Li and
Csaba Szepesv{\'{a}}ri and
Dale Schuurmans},
title = {On the Optimality of Batch Policy Optimization Algorithms},
journal = {CoRR},
volume = {abs/2104.02293},
year = {2021},
url = {https://arxiv.org/abs/2104.02293},
eprinttype = {arXiv},
eprint = {2104.02293},
timestamp = {Thu, 29 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2104-02293.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2105-06072,
author = {Jincheng Mei and
Yue Gao and
Bo Dai and
Csaba Szepesv{\'{a}}ri and
Dale Schuurmans},
title = {Leveraging Non-uniformity in First-order Non-convex Optimization},
journal = {CoRR},
volume = {abs/2105.06072},
year = {2021},
url = {https://arxiv.org/abs/2105.06072},
eprinttype = {arXiv},
eprint = {2105.06072},
timestamp = {Thu, 29 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2105-06072.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2106-08199,
author = {Abbas Abdolmaleki and
Sandy H. Huang and
Giulia Vezzani and
Bobak Shahriari and
Jost Tobias Springenberg and
Shruti Mishra and
Dhruva TB and
Arunkumar Byravan and
Konstantinos Bousmalis and
Andr{\'{a}}s Gy{\"{o}}rgy and
Csaba Szepesv{\'{a}}ri and
Raia Hadsell and
Nicolas Heess and
Martin A. Riedmiller},
title = {On Multi-objective Policy Optimization as a Tool for Reinforcement
Learning},
journal = {CoRR},
volume = {abs/2106.08199},
year = {2021},
url = {https://arxiv.org/abs/2106.08199},
eprinttype = {arXiv},
eprint = {2106.08199},
timestamp = {Sun, 02 Oct 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2106-08199.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2106-09973,
author = {Chenjun Xiao and
Ilbin Lee and
Bo Dai and
Dale Schuurmans and
Csaba Szepesv{\'{a}}ri},
title = {On the Sample Complexity of Batch Reinforcement Learning with Policy-Induced
Data},
journal = {CoRR},
volume = {abs/2106.09973},
year = {2021},
url = {https://arxiv.org/abs/2106.09973},
eprinttype = {arXiv},
eprint = {2106.09973},
timestamp = {Thu, 29 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2106-09973.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2107-06196,
author = {Soumya Basu and
Branislav Kveton and
Manzil Zaheer and
Csaba Szepesv{\'{a}}ri},
title = {No Regrets for Learning the Prior in Bandits},
journal = {CoRR},
volume = {abs/2107.06196},
year = {2021},
url = {https://arxiv.org/abs/2107.06196},
eprinttype = {arXiv},
eprint = {2107.06196},
timestamp = {Fri, 23 Jul 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2107-06196.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2107-12685,
author = {Ilja Kuzborskij and
Csaba Szepesv{\'{a}}ri and
Omar Rivasplata and
Amal Rannen{-}Triki and
Razvan Pascanu},
title = {On the Role of Optimization in Double Descent: {A} Least Squares Study},
journal = {CoRR},
volume = {abs/2107.12685},
year = {2021},
url = {https://arxiv.org/abs/2107.12685},
eprinttype = {arXiv},
eprint = {2107.12685},
timestamp = {Mon, 02 May 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2107-12685.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2108-05533,
author = {Dong Yin and
Botao Hao and
Yasin Abbasi{-}Yadkori and
Nevena Lazic and
Csaba Szepesv{\'{a}}ri},
title = {Efficient Local Planning with Linear Function Approximation},
journal = {CoRR},
volume = {abs/2108.05533},
year = {2021},
url = {https://arxiv.org/abs/2108.05533},
eprinttype = {arXiv},
eprint = {2108.05533},
timestamp = {Wed, 18 Aug 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2108-05533.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2110-02195,
author = {Gell{\'{e}}rt Weisz and
Csaba Szepesv{\'{a}}ri and
Andr{\'{a}}s Gy{\"{o}}rgy},
title = {TensorPlan and the Few Actions Lower Bound for Planning in MDPs under
Linear Realizability of Optimal Value Functions},
journal = {CoRR},
volume = {abs/2110.02195},
year = {2021},
url = {https://arxiv.org/abs/2110.02195},
eprinttype = {arXiv},
eprint = {2110.02195},
timestamp = {Mon, 18 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2110-02195.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2110-08984,
author = {Han Zhong and
Zhuoran Yang and
Zhaoran Wang and
Csaba Szepesv{\'{a}}ri},
title = {Optimistic Policy Optimization is Provably Efficient in Non-stationary
MDPs},
journal = {CoRR},
volume = {abs/2110.08984},
year = {2021},
url = {https://arxiv.org/abs/2110.08984},
eprinttype = {arXiv},
eprint = {2110.08984},
timestamp = {Wed, 27 Dec 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2110-08984.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2110-15572,
author = {Jincheng Mei and
Bo Dai and
Chenjun Xiao and
Csaba Szepesv{\'{a}}ri and
Dale Schuurmans},
title = {Understanding the Effect of Stochasticity in Policy Optimization},
journal = {CoRR},
volume = {abs/2110.15572},
year = {2021},
url = {https://arxiv.org/abs/2110.15572},
eprinttype = {arXiv},
eprint = {2110.15572},
timestamp = {Thu, 29 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2110-15572.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2111-11485,
author = {Tongzheng Ren and
Tianjun Zhang and
Csaba Szepesv{\'{a}}ri and
Bo Dai},
title = {A Free Lunch from the Noise: Provable and Practical Exploration for
Representation Learning},
journal = {CoRR},
volume = {abs/2111.11485},
year = {2021},
url = {https://arxiv.org/abs/2111.11485},
eprinttype = {arXiv},
eprint = {2111.11485},
timestamp = {Mon, 03 Jul 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2111-11485.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/aamas/TuylsPLHELSG20,
author = {Karl Tuyls and
Julien P{\'{e}}rolat and
Marc Lanctot and
Edward Hughes and
Richard Everett and
Joel Z. Leibo and
Csaba Szepesv{\'{a}}ri and
Thore Graepel},
title = {Bounds and dynamics for empirical game theoretic analysis},
journal = {Auton. Agents Multi Agent Syst.},
volume = {34},
number = {1},
pages = {7},
year = {2020},
url = {https://doi.org/10.1007/s10458-019-09432-y},
doi = {10.1007/S10458-019-09432-Y},
timestamp = {Fri, 09 Oct 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/aamas/TuylsPLHELSG20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/jmlr/MaOSS20,
author = {Yao Ma and
Alex Olshevsky and
Csaba Szepesv{\'{a}}ri and
Venkatesh Saligrama},
title = {Gradient Descent for Sparse Rank-One Matrix Completion for Crowd-Sourced
Aggregation of Sparsely Interacting Workers},
journal = {J. Mach. Learn. Res.},
volume = {21},
pages = {133:1--133:36},
year = {2020},
url = {http://jmlr.org/papers/v21/19-359.html},
timestamp = {Wed, 18 Nov 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/jmlr/MaOSS20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tcs/JoulaniGS20,
author = {Pooria Joulani and
Andr{\'{a}}s Gy{\"{o}}rgy and
Csaba Szepesv{\'{a}}ri},
title = {A modular analysis of adaptive (non-)convex optimization: Optimism,
composite objectives, variance reduction, and variational bounds},
journal = {Theor. Comput. Sci.},
volume = {808},
pages = {108--138},
year = {2020},
url = {https://doi.org/10.1016/j.tcs.2019.11.015},
doi = {10.1016/J.TCS.2019.11.015},
timestamp = {Tue, 19 May 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/tcs/JoulaniGS20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aistats/KvetonZS0GB20,
author = {Branislav Kveton and
Manzil Zaheer and
Csaba Szepesv{\'{a}}ri and
Lihong Li and
Mohammad Ghavamzadeh and
Craig Boutilier},
editor = {Silvia Chiappa and
Roberto Calandra},
title = {Randomized Exploration in Generalized Linear Bandits},
booktitle = {The 23rd International Conference on Artificial Intelligence and Statistics,
{AISTATS} 2020, 26-28 August 2020, Online [Palermo, Sicily, Italy]},
series = {Proceedings of Machine Learning Research},
volume = {108},
pages = {2066--2076},
publisher = {{PMLR}},
year = {2020},
url = {http://proceedings.mlr.press/v108/kveton20a.html},
timestamp = {Mon, 29 Jun 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/aistats/KvetonZS0GB20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aistats/HaoLS20,
author = {Botao Hao and
Tor Lattimore and
Csaba Szepesv{\'{a}}ri},
editor = {Silvia Chiappa and
Roberto Calandra},
title = {Adaptive Exploration in Linear Contextual Bandit},
booktitle = {The 23rd International Conference on Artificial Intelligence and Statistics,
{AISTATS} 2020, 26-28 August 2020, Online [Palermo, Sicily, Italy]},
series = {Proceedings of Machine Learning Research},
volume = {108},
pages = {3536--3545},
publisher = {{PMLR}},
year = {2020},
url = {http://proceedings.mlr.press/v108/hao20b.html},
timestamp = {Mon, 29 Jun 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/aistats/HaoLS20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/colt/LattimoreS20,
author = {Tor Lattimore and
Csaba Szepesv{\'{a}}ri},
editor = {Jacob D. Abernethy and
Shivani Agarwal},
title = {Exploration by Optimisation in Partial Monitoring},
booktitle = {Conference on Learning Theory, {COLT} 2020, 9-12 July 2020, Virtual
Event [Graz, Austria]},
series = {Proceedings of Machine Learning Research},
volume = {125},
pages = {2488--2515},
publisher = {{PMLR}},
year = {2020},
url = {http://proceedings.mlr.press/v125/lattimore20a.html},
timestamp = {Fri, 27 Nov 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/colt/LattimoreS20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iclr/OsbandDHASSMLSS20,
author = {Ian Osband and
Yotam Doron and
Matteo Hessel and
John Aslanides and
Eren Sezener and
Andre Saraiva and
Katrina McKinney and
Tor Lattimore and
Csaba Szepesv{\'{a}}ri and
Satinder Singh and
Benjamin Van Roy and
Richard S. Sutton and
David Silver and
Hado van Hasselt},
title = {Behaviour Suite for Reinforcement Learning},
booktitle = {8th International Conference on Learning Representations, {ICLR} 2020,
Addis Ababa, Ethiopia, April 26-30, 2020},
publisher = {OpenReview.net},
year = {2020},
url = {https://openreview.net/forum?id=rygf-kSYwH},
timestamp = {Mon, 15 May 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/iclr/OsbandDHASSMLSS20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/AyoubJSWY20,
author = {Alex Ayoub and
Zeyu Jia and
Csaba Szepesv{\'{a}}ri and
Mengdi Wang and
Lin Yang},
title = {Model-Based Reinforcement Learning with Value-Targeted Regression},
booktitle = {Proceedings of the 37th International Conference on Machine Learning,
{ICML} 2020, 13-18 July 2020, Virtual Event},
series = {Proceedings of Machine Learning Research},
volume = {119},
pages = {463--474},
publisher = {{PMLR}},
year = {2020},
url = {http://proceedings.mlr.press/v119/ayoub20a.html},
timestamp = {Sat, 30 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/AyoubJSWY20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/JoulaniRGS20,
author = {Pooria Joulani and
Anant Raj and
Andr{\'{a}}s Gy{\"{o}}rgy and
Csaba Szepesv{\'{a}}ri},
title = {A simpler approach to accelerated optimization: iterative averaging
meets optimism},
booktitle = {Proceedings of the 37th International Conference on Machine Learning,
{ICML} 2020, 13-18 July 2020, Virtual Event},
series = {Proceedings of Machine Learning Research},
volume = {119},
pages = {4984--4993},
publisher = {{PMLR}},
year = {2020},
url = {http://proceedings.mlr.press/v119/joulani20a.html},
timestamp = {Tue, 15 Dec 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icml/JoulaniRGS20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/LattimoreSW20,
author = {Tor Lattimore and
Csaba Szepesv{\'{a}}ri and
Gell{\'{e}}rt Weisz},
title = {Learning with Good Feature Representations in Bandits and in {RL}
with a Generative Model},
booktitle = {Proceedings of the 37th International Conference on Machine Learning,
{ICML} 2020, 13-18 July 2020, Virtual Event},
series = {Proceedings of Machine Learning Research},
volume = {119},
pages = {5662--5670},
publisher = {{PMLR}},
year = {2020},
url = {http://proceedings.mlr.press/v119/lattimore20a.html},
timestamp = {Tue, 15 Dec 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icml/LattimoreSW20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/MeiXSS20,
author = {Jincheng Mei and
Chenjun Xiao and
Csaba Szepesv{\'{a}}ri and
Dale Schuurmans},
title = {On the Global Convergence Rates of Softmax Policy Gradient Methods},
booktitle = {Proceedings of the 37th International Conference on Machine Learning,
{ICML} 2020, 13-18 July 2020, Virtual Event},
series = {Proceedings of Machine Learning Research},
volume = {119},
pages = {6820--6829},
publisher = {{PMLR}},
year = {2020},
url = {http://proceedings.mlr.press/v119/mei20b.html},
timestamp = {Tue, 15 Dec 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icml/MeiXSS20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/l4dc/JiaYSW20,
author = {Zeyu Jia and
Lin Yang and
Csaba Szepesv{\'{a}}ri and
Mengdi Wang},
editor = {Alexandre M. Bayen and
Ali Jadbabaie and
George J. Pappas and
Pablo A. Parrilo and
Benjamin Recht and
Claire J. Tomlin and
Melanie N. Zeilinger},
title = {Model-Based Reinforcement Learning with Value-Targeted Regression},
booktitle = {Proceedings of the 2nd Annual Conference on Learning for Dynamics
and Control, {L4DC} 2020, Online Event, Berkeley, CA, USA, 11-12 June
2020},
series = {Proceedings of Machine Learning Research},
volume = {120},
pages = {666--686},
publisher = {{PMLR}},
year = {2020},
url = {http://proceedings.mlr.press/v120/jia20a.html},
timestamp = {Sat, 30 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/l4dc/JiaYSW20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/BoutilierHKMSZ20,
author = {Craig Boutilier and
Chih{-}Wei Hsu and
Branislav Kveton and
Martin Mladenov and
Csaba Szepesv{\'{a}}ri and
Manzil Zaheer},
editor = {Hugo Larochelle and
Marc'Aurelio Ranzato and
Raia Hadsell and
Maria{-}Florina Balcan and
Hsuan{-}Tien Lin},
title = {Differentiable Meta-Learning of Bandit Policies},
booktitle = {Advances in Neural Information Processing Systems 33: Annual Conference
on Neural Information Processing Systems 2020, NeurIPS 2020, December
6-12, 2020, virtual},
year = {2020},
url = {https://proceedings.neurips.cc/paper/2020/hash/171ae1bbb81475eb96287dd78565b38b-Abstract.html},
timestamp = {Tue, 19 Jan 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/BoutilierHKMSZ20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/DaiNC0SS20,
author = {Bo Dai and
Ofir Nachum and
Yinlam Chow and
Lihong Li and
Csaba Szepesv{\'{a}}ri and
Dale Schuurmans},
editor = {Hugo Larochelle and
Marc'Aurelio Ranzato and
Raia Hadsell and
Maria{-}Florina Balcan and
Hsuan{-}Tien Lin},
title = {CoinDICE: Off-Policy Confidence Interval Estimation},
booktitle = {Advances in Neural Information Processing Systems 33: Annual Conference
on Neural Information Processing Systems 2020, NeurIPS 2020, December
6-12, 2020, virtual},
year = {2020},
url = {https://proceedings.neurips.cc/paper/2020/hash/6aaba9a124857622930ca4e50f5afed2-Abstract.html},
timestamp = {Thu, 29 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/nips/DaiNC0SS20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/MeiXD0SS20,
author = {Jincheng Mei and
Chenjun Xiao and
Bo Dai and
Lihong Li and
Csaba Szepesv{\'{a}}ri and
Dale Schuurmans},
editor = {Hugo Larochelle and
Marc'Aurelio Ranzato and
Raia Hadsell and
Maria{-}Florina Balcan and
Hsuan{-}Tien Lin},
title = {Escaping the Gravitational Pull of Softmax},
booktitle = {Advances in Neural Information Processing Systems 33: Annual Conference
on Neural Information Processing Systems 2020, NeurIPS 2020, December
6-12, 2020, virtual},
year = {2020},
url = {https://proceedings.neurips.cc/paper/2020/hash/f1cf2a082126bf02de0b307778ce73a7-Abstract.html},
timestamp = {Thu, 29 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/nips/MeiXD0SS20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/PacchianoPA0ZLS20,
author = {Aldo Pacchiano and
My Phan and
Yasin Abbasi{-}Yadkori and
Anup Rao and
Julian Zimmert and
Tor Lattimore and
Csaba Szepesv{\'{a}}ri},
editor = {Hugo Larochelle and
Marc'Aurelio Ranzato and
Raia Hadsell and
Maria{-}Florina Balcan and
Hsuan{-}Tien Lin},
title = {Model Selection in Contextual Stochastic Bandit Problems},
booktitle = {Advances in Neural Information Processing Systems 33: Annual Conference
on Neural Information Processing Systems 2020, NeurIPS 2020, December
6-12, 2020, virtual},
year = {2020},
url = {https://proceedings.neurips.cc/paper/2020/hash/751d51528afe5e6f7fe95dece4ed32ba-Abstract.html},
timestamp = {Tue, 19 Jan 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/PacchianoPA0ZLS20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/RivasplataKSS20,
author = {Omar Rivasplata and
Ilja Kuzborskij and
Csaba Szepesv{\'{a}}ri and
John Shawe{-}Taylor},
editor = {Hugo Larochelle and
Marc'Aurelio Ranzato and
Raia Hadsell and
Maria{-}Florina Balcan and
Hsuan{-}Tien Lin},
title = {PAC-Bayes Analysis Beyond the Usual Bounds},
booktitle = {Advances in Neural Information Processing Systems 33: Annual Conference
on Neural Information Processing Systems 2020, NeurIPS 2020, December
6-12, 2020, virtual},
year = {2020},
url = {https://proceedings.neurips.cc/paper/2020/hash/c3992e9a68c5ae12bd18488bc579b30d-Abstract.html},
timestamp = {Tue, 19 Jan 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/RivasplataKSS20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/ShariffS20,
author = {Roshan Shariff and
Csaba Szepesv{\'{a}}ri},
editor = {Hugo Larochelle and
Marc'Aurelio Ranzato and
Raia Hadsell and
Maria{-}Florina Balcan and
Hsuan{-}Tien Lin},
title = {Efficient Planning in Large MDPs with Weak Linear Function Approximation},
booktitle = {Advances in Neural Information Processing Systems 33: Annual Conference
on Neural Information Processing Systems 2020, NeurIPS 2020, December
6-12, 2020, virtual},
year = {2020},
url = {https://proceedings.neurips.cc/paper/2020/hash/de07edeeba9f475c9395959494cd8f64-Abstract.html},
timestamp = {Tue, 19 Jan 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/ShariffS20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/VermaHSS20,
author = {Arun Verma and
Manjesh Kumar Hanawal and
Csaba Szepesv{\'{a}}ri and
Venkatesh Saligrama},
editor = {Hugo Larochelle and
Marc'Aurelio Ranzato and
Raia Hadsell and
Maria{-}Florina Balcan and
Hsuan{-}Tien Lin},
title = {Online Algorithm for Unsupervised Sequential Selection with Contextual
Information},
booktitle = {Advances in Neural Information Processing Systems 33: Annual Conference
on Neural Information Processing Systems 2020, NeurIPS 2020, December
6-12, 2020, virtual},
year = {2020},
url = {https://proceedings.neurips.cc/paper/2020/hash/08e5d8066881eab185d0de9db3b36c7f-Abstract.html},
timestamp = {Tue, 19 Jan 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/VermaHSS20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/Weisz0LGLSL20,
author = {Gell{\'{e}}rt Weisz and
Andr{\'{a}}s Gy{\"{o}}rgy and
Wei{-}I Lin and
Devon R. Graham and
Kevin Leyton{-}Brown and
Csaba Szepesv{\'{a}}ri and
Brendan Lucier},
editor = {Hugo Larochelle and
Marc'Aurelio Ranzato and
Raia Hadsell and
Maria{-}Florina Balcan and
Hsuan{-}Tien Lin},
title = {ImpatientCapsAndRuns: Approximately Optimal Algorithm Configuration
from an Infinite Pool},
booktitle = {Advances in Neural Information Processing Systems 33: Annual Conference
on Neural Information Processing Systems 2020, NeurIPS 2020, December
6-12, 2020, virtual},
year = {2020},
url = {https://proceedings.neurips.cc/paper/2020/hash/ca5520b5672ea120b23bde75c46e76c6-Abstract.html},
timestamp = {Tue, 19 Jan 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/Weisz0LGLSL20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/ZhangKBSW20,
author = {Junyu Zhang and
Alec Koppel and
Amrit Singh Bedi and
Csaba Szepesv{\'{a}}ri and
Mengdi Wang},
editor = {Hugo Larochelle and
Marc'Aurelio Ranzato and
Raia Hadsell and
Maria{-}Florina Balcan and
Hsuan{-}Tien Lin},
title = {Variational Policy Gradient Method for Reinforcement Learning with
General Utilities},
booktitle = {Advances in Neural Information Processing Systems 33: Annual Conference
on Neural Information Processing Systems 2020, NeurIPS 2020, December
6-12, 2020, virtual},
year = {2020},
url = {https://proceedings.neurips.cc/paper/2020/hash/30ee748d38e21392de740e2f9dc686b6-Abstract.html},
timestamp = {Tue, 19 Jan 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/ZhangKBSW20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2002-03069,
author = {Botao Hao and
Nevena Lazic and
Yasin Abbasi{-}Yadkori and
Pooria Joulani and
Csaba Szepesv{\'{a}}ri},
title = {Provably Efficient Adaptive Approximate Policy Iteration},
journal = {CoRR},
volume = {abs/2002.03069},
year = {2020},
url = {https://arxiv.org/abs/2002.03069},
eprinttype = {arXiv},
eprint = {2002.03069},
timestamp = {Wed, 12 Feb 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2002-03069.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2002-06772,
author = {Craig Boutilier and
Chih{-}Wei Hsu and
Branislav Kveton and
Martin Mladenov and
Csaba Szepesv{\'{a}}ri and
Manzil Zaheer},
title = {Differentiable Bandit Exploration},
journal = {CoRR},
volume = {abs/2002.06772},
year = {2020},
url = {https://arxiv.org/abs/2002.06772},
eprinttype = {arXiv},
eprint = {2002.06772},
timestamp = {Mon, 02 Mar 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2002-06772.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2003-01704,
author = {Aldo Pacchiano and
My Phan and
Yasin Abbasi{-}Yadkori and
Anup Rao and
Julian Zimmert and
Tor Lattimore and
Csaba Szepesv{\'{a}}ri},
title = {Model Selection in Contextual Stochastic Bandit Problems},
journal = {CoRR},
volume = {abs/2003.01704},
year = {2020},
url = {https://arxiv.org/abs/2003.01704},
eprinttype = {arXiv},
eprint = {2003.01704},
timestamp = {Thu, 03 Sep 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2003-01704.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2005-06392,
author = {Jincheng Mei and
Chenjun Xiao and
Csaba Szepesv{\'{a}}ri and
Dale Schuurmans},
title = {On the Global Convergence Rates of Softmax Policy Gradient Methods},
journal = {CoRR},
volume = {abs/2005.06392},
year = {2020},
url = {https://arxiv.org/abs/2005.06392},
eprinttype = {arXiv},
eprint = {2005.06392},
timestamp = {Thu, 14 May 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2005-06392.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2006-01107,
author = {Alex Ayoub and
Zeyu Jia and
Csaba Szepesv{\'{a}}ri and
Mengdi Wang and
Lin F. Yang},
title = {Model-Based Reinforcement Learning with Value-Targeted Regression},
journal = {CoRR},
volume = {abs/2006.01107},
year = {2020},
url = {https://arxiv.org/abs/2006.01107},
eprinttype = {arXiv},
eprint = {2006.01107},
timestamp = {Sat, 23 Jan 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2006-01107.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2006-05094,
author = {Branislav Kveton and
Martin Mladenov and
Chih{-}Wei Hsu and
Manzil Zaheer and
Csaba Szepesv{\'{a}}ri and
Craig Boutilier},
title = {Differentiable Meta-Learning in Contextual Bandits},
journal = {CoRR},
volume = {abs/2006.05094},
year = {2020},
url = {https://arxiv.org/abs/2006.05094},
eprinttype = {arXiv},
eprint = {2006.05094},
timestamp = {Fri, 12 Jun 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2006-05094.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2006-10460,
author = {Ilja Kuzborskij and
Claire Vernade and
Andr{\'{a}}s Gy{\"{o}}rgy and
Csaba Szepesv{\'{a}}ri},
title = {Confident Off-Policy Evaluation and Selection through Self-Normalized
Importance Weighting},
journal = {CoRR},
volume = {abs/2006.10460},
year = {2020},
url = {https://arxiv.org/abs/2006.10460},
eprinttype = {arXiv},
eprint = {2006.10460},
timestamp = {Tue, 23 Jun 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2006-10460.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2006-13057,
author = {Omar Rivasplata and
Ilja Kuzborskij and
Csaba Szepesv{\'{a}}ri and
John Shawe{-}Taylor},
title = {PAC-Bayes Analysis Beyond the Usual Bounds},
journal = {CoRR},
volume = {abs/2006.13057},
year = {2020},
url = {https://arxiv.org/abs/2006.13057},
eprinttype = {arXiv},
eprint = {2006.13057},
timestamp = {Thu, 02 Jul 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2006-13057.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2007-02151,
author = {Junyu Zhang and
Alec Koppel and
Amrit Singh Bedi and
Csaba Szepesv{\'{a}}ri and
Mengdi Wang},
title = {Variational Policy Gradient Method for Reinforcement Learning with
General Utilities},
journal = {CoRR},
volume = {abs/2007.02151},
year = {2020},
url = {https://arxiv.org/abs/2007.02151},
eprinttype = {arXiv},
eprint = {2007.02151},
timestamp = {Fri, 17 Jul 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2007-02151.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2007-06184,
author = {Roshan Shariff and
Csaba Szepesv{\'{a}}ri},
title = {Efficient Planning in Large MDPs with Weak Linear Function Approximation},
journal = {CoRR},
volume = {abs/2007.06184},
year = {2020},
url = {https://arxiv.org/abs/2007.06184},
eprinttype = {arXiv},
eprint = {2007.06184},
timestamp = {Tue, 21 Jul 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2007-06184.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2007-12911,
author = {Mar{\'{\i}}a P{\'{e}}rez{-}Ortiz and
Omar Rivasplata and
John Shawe{-}Taylor and
Csaba Szepesv{\'{a}}ri},
title = {Tighter risk certificates for neural networks},
journal = {CoRR},
volume = {abs/2007.12911},
year = {2020},
url = {https://arxiv.org/abs/2007.12911},
eprinttype = {arXiv},
eprint = {2007.12911},
timestamp = {Mon, 26 Apr 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2007-12911.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2010-01374,
author = {Gell{\'{e}}rt Weisz and
Philip Amortila and
Csaba Szepesv{\'{a}}ri},
title = {Exponential Lower Bounds for Planning in MDPs With Linearly-Realizable
Optimal Action-Value Functions},
journal = {CoRR},
volume = {abs/2010.01374},
year = {2020},
url = {https://arxiv.org/abs/2010.01374},
eprinttype = {arXiv},
eprint = {2010.01374},
timestamp = {Mon, 12 Oct 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2010-01374.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2010-11652,
author = {Bo Dai and
Ofir Nachum and
Yinlam Chow and
Lihong Li and
Csaba Szepesv{\'{a}}ri and
Dale Schuurmans},
title = {CoinDICE: Off-Policy Confidence Interval Estimation},
journal = {CoRR},
volume = {abs/2010.11652},
year = {2020},
url = {https://arxiv.org/abs/2010.11652},
eprinttype = {arXiv},
eprint = {2010.11652},
timestamp = {Thu, 29 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2010-11652.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2010-12353,
author = {Arun Verma and
Manjesh Kumar Hanawal and
Csaba Szepesv{\'{a}}ri and
Venkatesh Saligrama},
title = {Online Algorithm for Unsupervised Sequential Selection with Contextual
Information},
journal = {CoRR},
volume = {abs/2010.12353},
year = {2020},
url = {https://arxiv.org/abs/2010.12353},
eprinttype = {arXiv},
eprint = {2010.12353},
timestamp = {Tue, 27 Oct 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2010-12353.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2011-00344,
author = {Mikhail Konobeev and
Ilja Kuzborskij and
Csaba Szepesv{\'{a}}ri},
title = {On Optimality of Meta-Learning in Fixed-Design Regression with Weighted
Biased Regularization},
journal = {CoRR},
volume = {abs/2011.00344},
year = {2020},
url = {https://arxiv.org/abs/2011.00344},
eprinttype = {arXiv},
eprint = {2011.00344},
timestamp = {Mon, 09 Nov 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2011-00344.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2011-04018,
author = {Botao Hao and
Tor Lattimore and
Csaba Szepesv{\'{a}}ri and
Mengdi Wang},
title = {Online Sparse Reinforcement Learning},
journal = {CoRR},
volume = {abs/2011.04018},
year = {2020},
url = {https://arxiv.org/abs/2011.04018},
eprinttype = {arXiv},
eprint = {2011.04018},
timestamp = {Thu, 12 Nov 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2011-04018.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2011-04019,
author = {Botao Hao and
Yaqi Duan and
Tor Lattimore and
Csaba Szepesv{\'{a}}ri and
Mengdi Wang},
title = {Sparse Feature Selection Makes Batch Reinforcement Learning More Sample
Efficient},
journal = {CoRR},
volume = {abs/2011.04019},
year = {2020},
url = {https://arxiv.org/abs/2011.04019},
eprinttype = {arXiv},
eprint = {2011.04019},
timestamp = {Thu, 12 Nov 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2011-04019.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2011-05944,
author = {Johannes Kirschner and
Tor Lattimore and
Claire Vernade and
Csaba Szepesv{\'{a}}ri},
title = {Asymptotically Optimal Information-Directed Sampling},
journal = {CoRR},
volume = {abs/2011.05944},
year = {2020},
url = {https://arxiv.org/abs/2011.05944},
eprinttype = {arXiv},
eprint = {2011.05944},
timestamp = {Thu, 12 Nov 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2011-05944.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2012-08507,
author = {Dongruo Zhou and
Quanquan Gu and
Csaba Szepesv{\'{a}}ri},
title = {Nearly Minimax Optimal Reinforcement Learning for Linear Mixture Markov
Decision Processes},
journal = {CoRR},
volume = {abs/2012.08507},
year = {2020},
url = {https://arxiv.org/abs/2012.08507},
eprinttype = {arXiv},
eprint = {2012.08507},
timestamp = {Sat, 02 Jan 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2012-08507.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/Abou-MoustafaS19,
author = {Karim T. Abou{-}Moustafa and
Csaba Szepesv{\'{a}}ri},
title = {An Exponential Tail Bound for the Deleted Estimate},
booktitle = {The Thirty-Third {AAAI} Conference on Artificial Intelligence, {AAAI}
2019, The Thirty-First Innovative Applications of Artificial Intelligence
Conference, {IAAI} 2019, The Ninth {AAAI} Symposium on Educational
Advances in Artificial Intelligence, {EAAI} 2019, Honolulu, Hawaii,
USA, January 27 - February 1, 2019},
pages = {3143--3150},
publisher = {{AAAI} Press},
year = {2019},
url = {https://doi.org/10.1609/aaai.v33i01.33013143},
doi = {10.1609/AAAI.V33I01.33013143},
timestamp = {Mon, 04 Sep 2023 12:29:24 +0200},
biburl = {https://dblp.org/rec/conf/aaai/Abou-MoustafaS19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aistats/Abbasi-YadkoriL19,
author = {Yasin Abbasi{-}Yadkori and
Nevena Lazic and
Csaba Szepesv{\'{a}}ri},
editor = {Kamalika Chaudhuri and
Masashi Sugiyama},
title = {Model-Free Linear Quadratic Control via Reduction to Expert Prediction},
booktitle = {The 22nd International Conference on Artificial Intelligence and Statistics,
{AISTATS} 2019, 16-18 April 2019, Naha, Okinawa, Japan},
series = {Proceedings of Machine Learning Research},
volume = {89},
pages = {3108--3117},
publisher = {{PMLR}},
year = {2019},
url = {http://proceedings.mlr.press/v89/abbasi-yadkori19a.html},
timestamp = {Fri, 07 Jun 2019 09:03:47 +0200},
biburl = {https://dblp.org/rec/conf/aistats/Abbasi-YadkoriL19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aistats/VermaHSS19,
author = {Arun Verma and
Manjesh Kumar Hanawal and
Csaba Szepesv{\'{a}}ri and
Venkatesh Saligrama},
editor = {Kamalika Chaudhuri and
Masashi Sugiyama},
title = {Online Algorithm for Unsupervised Sensor Selection},
booktitle = {The 22nd International Conference on Artificial Intelligence and Statistics,
{AISTATS} 2019, 16-18 April 2019, Naha, Okinawa, Japan},
series = {Proceedings of Machine Learning Research},
volume = {89},
pages = {3168--3176},
publisher = {{PMLR}},
year = {2019},
url = {http://proceedings.mlr.press/v89/verma19a.html},
timestamp = {Fri, 09 Oct 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/aistats/VermaHSS19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/alt/Abou-MoustafaS19,
author = {Karim T. Abou{-}Moustafa and
Csaba Szepesv{\'{a}}ri},
editor = {Aur{\'{e}}lien Garivier and
Satyen Kale},
title = {An Exponential Efron-Stein Inequality for \emph{L\({}_{\mbox{q}}\)}
Stable Learning Rules},
booktitle = {Algorithmic Learning Theory, {ALT} 2019, 22-24 March 2019, Chicago,
Illinois, {USA}},
series = {Proceedings of Machine Learning Research},
volume = {98},
pages = {31--63},
publisher = {{PMLR}},
year = {2019},
url = {http://proceedings.mlr.press/v98/abou-moustafa19a.html},
timestamp = {Tue, 11 Apr 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/alt/Abou-MoustafaS19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/alt/LattimoreS19,
author = {Tor Lattimore and
Csaba Szepesv{\'{a}}ri},
editor = {Aur{\'{e}}lien Garivier and
Satyen Kale},
title = {Cleaning up the neighborhood: {A} full classification for adversarial
partial monitoring},
booktitle = {Algorithmic Learning Theory, {ALT} 2019, 22-24 March 2019, Chicago,
Illinois, {USA}},
series = {Proceedings of Machine Learning Research},
volume = {98},
pages = {529--556},
publisher = {{PMLR}},
year = {2019},
url = {http://proceedings.mlr.press/v98/lattimore19a.html},
timestamp = {Wed, 29 May 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/alt/LattimoreS19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/colt/KuzborskijCS19,
author = {Ilja Kuzborskij and
Nicol{\`{o}} Cesa{-}Bianchi and
Csaba Szepesv{\'{a}}ri},
editor = {Alina Beygelzimer and
Daniel Hsu},
title = {Distribution-Dependent Analysis of Gibbs-ERM Principle},
booktitle = {Conference on Learning Theory, {COLT} 2019, 25-28 June 2019, Phoenix,
AZ, {USA}},
series = {Proceedings of Machine Learning Research},
volume = {99},
pages = {2028--2054},
publisher = {{PMLR}},
year = {2019},
url = {http://proceedings.mlr.press/v99/kuzborskij19a.html},
timestamp = {Mon, 08 Jul 2019 16:13:41 +0200},
biburl = {https://dblp.org/rec/conf/colt/KuzborskijCS19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/colt/LattimoreS19,
author = {Tor Lattimore and
Csaba Szepesv{\'{a}}ri},
editor = {Alina Beygelzimer and
Daniel Hsu},
title = {An Information-Theoretic Approach to Minimax Regret in Partial Monitoring},
booktitle = {Conference on Learning Theory, {COLT} 2019, 25-28 June 2019, Phoenix,
AZ, {USA}},
series = {Proceedings of Machine Learning Research},
volume = {99},
pages = {2111--2139},
publisher = {{PMLR}},
year = {2019},
url = {http://proceedings.mlr.press/v99/lattimore19a.html},
timestamp = {Mon, 08 Jul 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/colt/LattimoreS19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iclr/UesatoKSERADHK19,
author = {Jonathan Uesato and
Ananya Kumar and
Csaba Szepesv{\'{a}}ri and
Tom Erez and
Avraham Ruderman and
Keith Anderson and
Krishnamurthy (Dj) Dvijotham and
Nicolas Heess and
Pushmeet Kohli},
title = {Rigorous Agent Evaluation: An Adversarial Approach to Uncover Catastrophic
Failures},
booktitle = {7th International Conference on Learning Representations, {ICLR} 2019,
New Orleans, LA, USA, May 6-9, 2019},
publisher = {OpenReview.net},
year = {2019},
url = {https://openreview.net/forum?id=B1xhQhRcK7},
timestamp = {Thu, 25 Jul 2019 13:03:15 +0200},
biburl = {https://dblp.org/rec/conf/iclr/UesatoKSERADHK19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/KvetonSVWLG19,
author = {Branislav Kveton and
Csaba Szepesv{\'{a}}ri and
Sharan Vaswani and
Zheng Wen and
Tor Lattimore and
Mohammad Ghavamzadeh},
editor = {Kamalika Chaudhuri and
Ruslan Salakhutdinov},
title = {Garbage In, Reward Out: Bootstrapping Exploration in Multi-Armed Bandits},
booktitle = {Proceedings of the 36th International Conference on Machine Learning,
{ICML} 2019, 9-15 June 2019, Long Beach, California, {USA}},
series = {Proceedings of Machine Learning Research},
volume = {97},
pages = {3601--3610},
publisher = {{PMLR}},
year = {2019},
url = {http://proceedings.mlr.press/v97/kveton19a.html},
timestamp = {Tue, 11 Jun 2019 15:37:38 +0200},
biburl = {https://dblp.org/rec/conf/icml/KvetonSVWLG19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/X19,
editor = {Kamalika Chaudhuri and
Ruslan Salakhutdinov},
title = {{POLITEX:} Regret Bounds for Policy Iteration using Expert Prediction},
booktitle = {Proceedings of the 36th International Conference on Machine Learning,
{ICML} 2019, 9-15 June 2019, Long Beach, California, {USA}},
series = {Proceedings of Machine Learning Research},
volume = {97},
pages = {3692--3702},
publisher = {{PMLR}},
year = {2019},
url = {http://proceedings.mlr.press/v97/lazic19a.html},
timestamp = {Tue, 08 Oct 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/X19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/LiLS19,
author = {Shuai Li and
Tor Lattimore and
Csaba Szepesv{\'{a}}ri},
editor = {Kamalika Chaudhuri and
Ruslan Salakhutdinov},
title = {Online Learning to Rank with Features},
booktitle = {Proceedings of the 36th International Conference on Machine Learning,
{ICML} 2019, 9-15 June 2019, Long Beach, California, {USA}},
series = {Proceedings of Machine Learning Research},
volume = {97},
pages = {3856--3865},
publisher = {{PMLR}},
year = {2019},
url = {http://proceedings.mlr.press/v97/li19f.html},
timestamp = {Tue, 11 Jun 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/LiLS19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/WeiszGS19,
author = {Gell{\'{e}}rt Weisz and
Andr{\'{a}}s Gy{\"{o}}rgy and
Csaba Szepesv{\'{a}}ri},
editor = {Kamalika Chaudhuri and
Ruslan Salakhutdinov},
title = {CapsAndRuns: An Improved Method for Approximately Optimal Algorithm
Configuration},
booktitle = {Proceedings of the 36th International Conference on Machine Learning,
{ICML} 2019, 9-15 June 2019, Long Beach, California, {USA}},
series = {Proceedings of Machine Learning Research},
volume = {97},
pages = {6707--6715},
publisher = {{PMLR}},
year = {2019},
url = {http://proceedings.mlr.press/v97/weisz19a.html},
timestamp = {Tue, 19 May 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/WeiszGS19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ijcai/KvetonSGB19,
author = {Branislav Kveton and
Csaba Szepesv{\'{a}}ri and
Mohammad Ghavamzadeh and
Craig Boutilier},
editor = {Sarit Kraus},
title = {Perturbed-History Exploration in Stochastic Multi-Armed Bandits},
booktitle = {Proceedings of the Twenty-Eighth International Joint Conference on
Artificial Intelligence, {IJCAI} 2019, Macao, China, August 10-16,
2019},
pages = {2786--2793},
publisher = {ijcai.org},
year = {2019},
url = {https://doi.org/10.24963/ijcai.2019/386},
doi = {10.24963/IJCAI.2019/386},
timestamp = {Tue, 20 Aug 2019 16:18:18 +0200},
biburl = {https://dblp.org/rec/conf/ijcai/KvetonSGB19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/WerpachowskiGS19,
author = {Roman Werpachowski and
Andr{\'{a}}s Gy{\"{o}}rgy and
Csaba Szepesv{\'{a}}ri},
editor = {Hanna M. Wallach and
Hugo Larochelle and
Alina Beygelzimer and
Florence d'Alch{\'{e}}{-}Buc and
Emily B. Fox and
Roman Garnett},
title = {Detecting Overfitting via Adversarial Examples},
booktitle = {Advances in Neural Information Processing Systems 32: Annual Conference
on Neural Information Processing Systems 2019, NeurIPS 2019, December
8-14, 2019, Vancouver, BC, Canada},
pages = {7856--7866},
year = {2019},
url = {https://proceedings.neurips.cc/paper/2019/hash/28f7241796510e838db4a1384ae1279d-Abstract.html},
timestamp = {Mon, 16 May 2022 15:41:51 +0200},
biburl = {https://dblp.org/rec/conf/nips/WerpachowskiGS19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/JoulaniGS19,
author = {Pooria Joulani and
Andr{\'{a}}s Gy{\"{o}}rgy and
Csaba Szepesv{\'{a}}ri},
editor = {Hanna M. Wallach and
Hugo Larochelle and
Alina Beygelzimer and
Florence d'Alch{\'{e}}{-}Buc and
Emily B. Fox and
Roman Garnett},
title = {Think out of the "Box": Generically-Constrained Asynchronous
Composite Optimization and Hedging},
booktitle = {Advances in Neural Information Processing Systems 32: Annual Conference
on Neural Information Processing Systems 2019, NeurIPS 2019, December
8-14, 2019, Vancouver, BC, Canada},
pages = {12225--12235},
year = {2019},
url = {https://proceedings.neurips.cc/paper/2019/hash/0224cd598e48c5041c7947fd5cb20d53-Abstract.html},
timestamp = {Thu, 21 Jan 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/JoulaniGS19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/uai/0003KLMRSZ19,
author = {Chang Li and
Branislav Kveton and
Tor Lattimore and
Ilya Markov and
Maarten de Rijke and
Csaba Szepesv{\'{a}}ri and
Masrour Zoghi},
editor = {Amir Globerson and
Ricardo Silva},
title = {BubbleRank: Safe Online Learning to Re-Rank via Implicit Click Feedback},
booktitle = {Proceedings of the Thirty-Fifth Conference on Uncertainty in Artificial
Intelligence, {UAI} 2019, Tel Aviv, Israel, July 22-25, 2019},
series = {Proceedings of Machine Learning Research},
volume = {115},
pages = {196--206},
publisher = {{AUAI} Press},
year = {2019},
url = {http://proceedings.mlr.press/v115/li20b.html},
timestamp = {Tue, 15 Dec 2020 17:40:18 +0100},
biburl = {https://dblp.org/rec/conf/uai/0003KLMRSZ19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/uai/KvetonSGB19,
author = {Branislav Kveton and
Csaba Szepesv{\'{a}}ri and
Mohammad Ghavamzadeh and
Craig Boutilier},
editor = {Amir Globerson and
Ricardo Silva},
title = {Perturbed-History Exploration in Stochastic Linear Bandits},
booktitle = {Proceedings of the Thirty-Fifth Conference on Uncertainty in Artificial
Intelligence, {UAI} 2019, Tel Aviv, Israel, July 22-25, 2019},
series = {Proceedings of Machine Learning Research},
volume = {115},
pages = {530--540},
publisher = {{AUAI} Press},
year = {2019},
url = {http://proceedings.mlr.press/v115/kveton20a.html},
timestamp = {Tue, 15 Dec 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/uai/KvetonSGB19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1901-04676,
author = {Arun Verma and
Manjesh Kumar Hanawal and
Csaba Szepesv{\'{a}}ri and
Venkatesh Saligrama},
title = {Online Algorithm for Unsupervised Sensor Selection},
journal = {CoRR},
volume = {abs/1901.04676},
year = {2019},
url = {http://arxiv.org/abs/1901.04676},
eprinttype = {arXiv},
eprint = {1901.04676},
timestamp = {Fri, 09 Oct 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1901-04676.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1902-00470,
author = {Tor Lattimore and
Csaba Szepesv{\'{a}}ri},
title = {An Information-Theoretic Approach to Minimax Regret in Partial Monitoring},
journal = {CoRR},
volume = {abs/1902.00470},
year = {2019},
url = {http://arxiv.org/abs/1902.00470},
eprinttype = {arXiv},
eprint = {1902.00470},
timestamp = {Tue, 21 May 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1902-00470.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1902-01846,
author = {Ilja Kuzborskij and
Nicol{\`{o}} Cesa{-}Bianchi and
Csaba Szepesv{\'{a}}ri},
title = {Distribution-Dependent Analysis of Gibbs-ERM Principle},
journal = {CoRR},
volume = {abs/1902.01846},
year = {2019},
url = {http://arxiv.org/abs/1902.01846},
eprinttype = {arXiv},
eprint = {1902.01846},
timestamp = {Tue, 21 May 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1902-01846.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1902-10089,
author = {Branislav Kveton and
Csaba Szepesv{\'{a}}ri and
Mohammad Ghavamzadeh and
Craig Boutilier},
title = {Perturbed-History Exploration in Stochastic Multi-Armed Bandits},
journal = {CoRR},
volume = {abs/1902.10089},
year = {2019},
url = {http://arxiv.org/abs/1902.10089},
eprinttype = {arXiv},
eprint = {1902.10089},
timestamp = {Tue, 21 May 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1902-10089.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1903-02380,
author = {Roman Werpachowski and
Andr{\'{a}}s Gy{\"{o}}rgy and
Csaba Szepesv{\'{a}}ri},
title = {Detecting Overfitting via Adversarial Examples},
journal = {CoRR},
volume = {abs/1903.02380},
year = {2019},
url = {http://arxiv.org/abs/1903.02380},
eprinttype = {arXiv},
eprint = {1903.02380},
timestamp = {Sat, 23 Jan 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-1903-02380.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1903-05457,
author = {Karim T. Abou{-}Moustafa and
Csaba Szepesv{\'{a}}ri},
title = {An Exponential Efron-Stein Inequality for Lq Stable Learning Rules},
journal = {CoRR},
volume = {abs/1903.05457},
year = {2019},
url = {http://arxiv.org/abs/1903.05457},
eprinttype = {arXiv},
eprint = {1903.05457},
timestamp = {Tue, 02 Apr 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1903-05457.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1903-09132,
author = {Branislav Kveton and
Csaba Szepesv{\'{a}}ri and
Mohammad Ghavamzadeh and
Craig Boutilier},
title = {Perturbed-History Exploration in Stochastic Linear Bandits},
journal = {CoRR},
volume = {abs/1903.09132},
year = {2019},
url = {http://arxiv.org/abs/1903.09132},
eprinttype = {arXiv},
eprint = {1903.09132},
timestamp = {Mon, 01 Apr 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1903-09132.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1904-02664,
author = {Chih{-}Wei Hsu and
Branislav Kveton and
Ofer Meshi and
Martin Mladenov and
Csaba Szepesv{\'{a}}ri},
title = {Empirical Bayes Regret Minimization},
journal = {CoRR},
volume = {abs/1904.02664},
year = {2019},
url = {http://arxiv.org/abs/1904.02664},
eprinttype = {arXiv},
eprint = {1904.02664},
timestamp = {Wed, 24 Apr 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1904-02664.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1904-11608,
author = {Yao Ma and
Alex Olshevsky and
Venkatesh Saligrama and
Csaba Szepesv{\'{a}}ri},
title = {Gradient Descent for Sparse Rank-One Matrix Completion for Crowd-Sourced
Aggregation of Sparsely Interacting Workers},
journal = {CoRR},
volume = {abs/1904.11608},
year = {2019},
url = {http://arxiv.org/abs/1904.11608},
eprinttype = {arXiv},
eprint = {1904.11608},
timestamp = {Thu, 02 May 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1904-11608.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1906-08947,
author = {Branislav Kveton and
Manzil Zaheer and
Csaba Szepesv{\'{a}}ri and
Lihong Li and
Mohammad Ghavamzadeh and
Craig Boutilier},
title = {Randomized Exploration in Generalized Linear Bandits},
journal = {CoRR},
volume = {abs/1906.08947},
year = {2019},
url = {http://arxiv.org/abs/1906.08947},
eprinttype = {arXiv},
eprint = {1906.08947},
timestamp = {Sun, 30 Jun 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1906-08947.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1907-05772,
author = {Tor Lattimore and
Csaba Szepesv{\'{a}}ri},
title = {Exploration by Optimisation in Partial Monitoring},
journal = {CoRR},
volume = {abs/1907.05772},
year = {2019},
url = {http://arxiv.org/abs/1907.05772},
eprinttype = {arXiv},
eprint = {1907.05772},
timestamp = {Wed, 17 Jul 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1907-05772.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1908-03568,
author = {Ian Osband and
Yotam Doron and
Matteo Hessel and
John Aslanides and
Eren Sezener and
Andre Saraiva and
Katrina McKinney and
Tor Lattimore and
Csaba Szepesv{\'{a}}ri and
Satinder Singh and
Benjamin Van Roy and
Richard S. Sutton and
David Silver and
Hado van Hasselt},
title = {Behaviour Suite for Reinforcement Learning},
journal = {CoRR},
volume = {abs/1908.03568},
year = {2019},
url = {http://arxiv.org/abs/1908.03568},
eprinttype = {arXiv},
eprint = {1908.03568},
timestamp = {Mon, 15 May 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1908-03568.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1908-07380,
author = {Omar Rivasplata and
Vikram M. Tankasali and
Csaba Szepesv{\'{a}}ri},
title = {PAC-Bayes with Backprop},
journal = {CoRR},
volume = {abs/1908.07380},
year = {2019},
url = {http://arxiv.org/abs/1908.07380},
eprinttype = {arXiv},
eprint = {1908.07380},
timestamp = {Mon, 26 Aug 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1908-07380.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1908-10479,
author = {Yasin Abbasi{-}Yadkori and
Nevena Lazic and
Csaba Szepesv{\'{a}}ri and
Gell{\'{e}}rt Weisz},
title = {Exploration-Enhanced {POLITEX}},
journal = {CoRR},
volume = {abs/1908.10479},
year = {2019},
url = {http://arxiv.org/abs/1908.10479},
eprinttype = {arXiv},
eprint = {1908.10479},
timestamp = {Thu, 29 Aug 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1908-10479.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1909-01931,
author = {Ilja Kuzborskij and
Csaba Szepesv{\'{a}}ri},
title = {Efron-Stein PAC-Bayesian Inequalities},
journal = {CoRR},
volume = {abs/1909.01931},
year = {2019},
url = {http://arxiv.org/abs/1909.01931},
eprinttype = {arXiv},
eprint = {1909.01931},
timestamp = {Mon, 16 Sep 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1909-01931.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1910-06996,
author = {Botao Hao and
Tor Lattimore and
Csaba Szepesv{\'{a}}ri},
title = {Adaptive Exploration in Linear Contextual Bandit},
journal = {CoRR},
volume = {abs/1910.06996},
year = {2019},
url = {http://arxiv.org/abs/1910.06996},
eprinttype = {arXiv},
eprint = {1910.06996},
timestamp = {Tue, 22 Oct 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1910-06996.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1910-08446,
author = {Pratik Gajane and
Ronald Ortner and
Peter Auer and
Csaba Szepesv{\'{a}}ri},
title = {Autonomous exploration for navigating in non-stationary CMPs},
journal = {CoRR},
volume = {abs/1910.08446},
year = {2019},
url = {http://arxiv.org/abs/1910.08446},
eprinttype = {arXiv},
eprint = {1910.08446},
timestamp = {Tue, 22 Oct 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1910-08446.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1911-07676,
author = {Tor Lattimore and
Csaba Szepesv{\'{a}}ri},
title = {Learning with Good Feature Representations in Bandits and in {RL}
with a Generative Model},
journal = {CoRR},
volume = {abs/1911.07676},
year = {2019},
url = {http://arxiv.org/abs/1911.07676},
eprinttype = {arXiv},
eprint = {1911.07676},
timestamp = {Wed, 04 Dec 2019 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-1911-07676.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tac/Lakshminarayanan18,
author = {Chandrashekar Lakshminarayanan and
Shalabh Bhatnagar and
Csaba Szepesv{\'{a}}ri},
title = {A Linearly Relaxed Approximate Linear Program for Markov Decision
Processes},
journal = {{IEEE} Trans. Autom. Control.},
volume = {63},
number = {4},
pages = {1185--1191},
year = {2018},
url = {https://doi.org/10.1109/TAC.2017.2743163},
doi = {10.1109/TAC.2017.2743163},
timestamp = {Wed, 20 May 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/tac/Lakshminarayanan18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tac/JieAFMS18,
author = {Cheng Jie and
Prashanth L. A. and
Michael C. Fu and
Steven I. Marcus and
Csaba Szepesv{\'{a}}ri},
title = {Stochastic Optimization in a Cumulative Prospect Theory Framework},
journal = {{IEEE} Trans. Autom. Control.},
volume = {63},
number = {9},
pages = {2867--2882},
year = {2018},
url = {https://doi.org/10.1109/TAC.2018.2822658},
doi = {10.1109/TAC.2018.2822658},
timestamp = {Wed, 20 May 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/tac/JieAFMS18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aistats/Lakshminarayanan18,
author = {Chandrashekar Lakshminarayanan and
Csaba Szepesv{\'{a}}ri},
editor = {Amos J. Storkey and
Fernando P{\'{e}}rez{-}Cruz},
title = {Linear Stochastic Approximation: How Far Does Constant Step-Size and
Iterate Averaging Go?},
booktitle = {International Conference on Artificial Intelligence and Statistics,
{AISTATS} 2018, 9-11 April 2018, Playa Blanca, Lanzarote, Canary Islands,
Spain},
series = {Proceedings of Machine Learning Research},
volume = {84},
pages = {1347--1355},
publisher = {{PMLR}},
year = {2018},
url = {http://proceedings.mlr.press/v84/lakshminarayanan18a.html},
timestamp = {Wed, 03 Apr 2019 18:17:22 +0200},
biburl = {https://dblp.org/rec/conf/aistats/Lakshminarayanan18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/MaOSS18,
author = {Yao Ma and
Alexander Olshevsky and
Csaba Szepesv{\'{a}}ri and
Venkatesh Saligrama},
editor = {Jennifer G. Dy and
Andreas Krause},
title = {Gradient Descent for Sparse Rank-One Matrix Completion for Crowd-Sourced
Aggregation of Sparsely Interacting Workers},
booktitle = {Proceedings of the 35th International Conference on Machine Learning,
{ICML} 2018, Stockholmsm{\"{a}}ssan, Stockholm, Sweden, July
10-15, 2018},
series = {Proceedings of Machine Learning Research},
volume = {80},
pages = {3341--3350},
publisher = {{PMLR}},
year = {2018},
url = {http://proceedings.mlr.press/v80/ma18b.html},
timestamp = {Wed, 03 Apr 2019 18:17:30 +0200},
biburl = {https://dblp.org/rec/conf/icml/MaOSS18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/Pike-Burke0SG18,
author = {Ciara Pike{-}Burke and
Shipra Agrawal and
Csaba Szepesv{\'{a}}ri and
Steffen Gr{\"{u}}new{\"{a}}lder},
editor = {Jennifer G. Dy and
Andreas Krause},
title = {Bandits with Delayed, Aggregated Anonymous Feedback},
booktitle = {Proceedings of the 35th International Conference on Machine Learning,
{ICML} 2018, Stockholmsm{\"{a}}ssan, Stockholm, Sweden, July
10-15, 2018},
series = {Proceedings of Machine Learning Research},
volume = {80},
pages = {4102--4110},
publisher = {{PMLR}},
year = {2018},
url = {http://proceedings.mlr.press/v80/pike-burke18a.html},
timestamp = {Wed, 03 Apr 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/Pike-Burke0SG18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/WeiszGS18,
author = {Gell{\'{e}}rt Weisz and
Andr{\'{a}}s Gy{\"{o}}rgy and
Csaba Szepesv{\'{a}}ri},
editor = {Jennifer G. Dy and
Andreas Krause},
title = {{LEAPSANDBOUNDS:} {A} Method for Approximately Optimal Algorithm Configuration},
booktitle = {Proceedings of the 35th International Conference on Machine Learning,
{ICML} 2018, Stockholmsm{\"{a}}ssan, Stockholm, Sweden, July
10-15, 2018},
series = {Proceedings of Machine Learning Research},
volume = {80},
pages = {5254--5262},
publisher = {{PMLR}},
year = {2018},
url = {http://proceedings.mlr.press/v80/weisz18a.html},
timestamp = {Tue, 19 May 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/WeiszGS18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/isaim/Abou-MoustafaS18,
author = {Karim T. Abou{-}Moustafa and
Csaba Szepesv{\'{a}}ri},
title = {An Exponential Tail Bound for Lq Stable Learning Rules. Application
to k-Folds Cross-Validation},
booktitle = {International Symposium on Artificial Intelligence and Mathematics,
{ISAIM} 2018, Fort Lauderdale, Florida, USA, January 3-5, 2018},
year = {2018},
url = {https://isaim2018.cs.ou.edu/papers/ISAIM2018\_Abou-Moustafa\_Szepesvari.pdf},
timestamp = {Wed, 20 Mar 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/isaim/Abou-MoustafaS18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/LattimoreKLS18,
author = {Tor Lattimore and
Branislav Kveton and
Shuai Li and
Csaba Szepesv{\'{a}}ri},
editor = {Samy Bengio and
Hanna M. Wallach and
Hugo Larochelle and
Kristen Grauman and
Nicol{\`{o}} Cesa{-}Bianchi and
Roman Garnett},
title = {TopRank: {A} practical algorithm for online stochastic ranking},
booktitle = {Advances in Neural Information Processing Systems 31: Annual Conference
on Neural Information Processing Systems 2018, NeurIPS 2018, December
3-8, 2018, Montr{\'{e}}al, Canada},
pages = {3949--3958},
year = {2018},
url = {https://proceedings.neurips.cc/paper/2018/hash/de03beffeed9da5f3639a621bcab5dd4-Abstract.html},
timestamp = {Mon, 16 May 2022 15:41:51 +0200},
biburl = {https://dblp.org/rec/conf/nips/LattimoreKLS18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/RivasplataSSPS18,
author = {Omar Rivasplata and
Csaba Szepesv{\'{a}}ri and
John Shawe{-}Taylor and
Emilio Parrado{-}Hern{\'{a}}ndez and
Shiliang Sun},
editor = {Samy Bengio and
Hanna M. Wallach and
Hugo Larochelle and
Kristen Grauman and
Nicol{\`{o}} Cesa{-}Bianchi and
Roman Garnett},
title = {PAC-Bayes bounds for stable algorithms with instance-dependent priors},
booktitle = {Advances in Neural Information Processing Systems 31: Annual Conference
on Neural Information Processing Systems 2018, NeurIPS 2018, December
3-8, 2018, Montr{\'{e}}al, Canada},
pages = {9234--9244},
year = {2018},
url = {https://proceedings.neurips.cc/paper/2018/hash/386854131f58a556343e056f03626e00-Abstract.html},
timestamp = {Thu, 21 Jan 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/RivasplataSSPS18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1804-06021,
author = {Yasin Abbasi{-}Yadkori and
Nevena Lazic and
Csaba Szepesv{\'{a}}ri},
title = {Regret Bounds for Model-Free Linear Quadratic Control},
journal = {CoRR},
volume = {abs/1804.06021},
year = {2018},
url = {http://arxiv.org/abs/1804.06021},
eprinttype = {arXiv},
eprint = {1804.06021},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1804-06021.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1805-09247,
author = {Tor Lattimore and
Csaba Szepesv{\'{a}}ri},
title = {Cleaning up the neighborhood: {A} full classification for adversarial
partial monitoring},
journal = {CoRR},
volume = {abs/1805.09247},
year = {2018},
url = {http://arxiv.org/abs/1805.09247},
eprinttype = {arXiv},
eprint = {1805.09247},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1805-09247.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1806-02248,
author = {Tor Lattimore and
Branislav Kveton and
Shuai Li and
Csaba Szepesv{\'{a}}ri},
title = {TopRank: {A} practical algorithm for online stochastic ranking},
journal = {CoRR},
volume = {abs/1806.02248},
year = {2018},
url = {http://arxiv.org/abs/1806.02248},
eprinttype = {arXiv},
eprint = {1806.02248},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1806-02248.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1806-05819,
author = {Branislav Kveton and
Chang Li and
Tor Lattimore and
Ilya Markov and
Maarten de Rijke and
Csaba Szepesv{\'{a}}ri and
Masrour Zoghi},
title = {BubbleRank: Safe Online Learning to Rerank},
journal = {CoRR},
volume = {abs/1806.05819},
year = {2018},
url = {http://arxiv.org/abs/1806.05819},
eprinttype = {arXiv},
eprint = {1806.05819},
timestamp = {Wed, 09 Jan 2019 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-1806-05819.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1806-06827,
author = {Omar Rivasplata and
Emilio Parrado{-}Hern{\'{a}}ndez and
John Shawe{-}Taylor and
Shiliang Sun and
Csaba Szepesv{\'{a}}ri},
title = {PAC-Bayes bounds for stable algorithms with instance-dependent priors},
journal = {CoRR},
volume = {abs/1806.06827},
year = {2018},
url = {http://arxiv.org/abs/1806.06827},
eprinttype = {arXiv},
eprint = {1806.06827},
timestamp = {Sat, 23 Jan 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-1806-06827.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1807-00755,
author = {Gell{\'{e}}rt Weisz and
Andr{\'{a}}s Gy{\"{o}}rgy and
Csaba Szepesv{\'{a}}ri},
title = {LeapsAndBounds: {A} Method for Approximately Optimal Algorithm Configuration},
journal = {CoRR},
volume = {abs/1807.00755},
year = {2018},
url = {http://arxiv.org/abs/1807.00755},
eprinttype = {arXiv},
eprint = {1807.00755},
timestamp = {Tue, 19 May 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1807-00755.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1810-02567,
author = {Shuai Li and
Tor Lattimore and
Csaba Szepesv{\'{a}}ri},
title = {Online Learning to Rank with Features},
journal = {CoRR},
volume = {abs/1810.02567},
year = {2018},
url = {http://arxiv.org/abs/1810.02567},
eprinttype = {arXiv},
eprint = {1810.02567},
timestamp = {Thu, 01 Nov 2018 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-1810-02567.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1811-05154,
author = {Branislav Kveton and
Csaba Szepesv{\'{a}}ri and
Zheng Wen and
Mohammad Ghavamzadeh and
Tor Lattimore},
title = {Garbage In, Reward Out: Bootstrapping Exploration in Multi-Armed Bandits},
journal = {CoRR},
volume = {abs/1811.05154},
year = {2018},
url = {http://arxiv.org/abs/1811.05154},
eprinttype = {arXiv},
eprint = {1811.05154},
timestamp = {Sat, 24 Nov 2018 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-1811-05154.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1812-01647,
author = {Jonathan Uesato and
Ananya Kumar and
Csaba Szepesv{\'{a}}ri and
Tom Erez and
Avraham Ruderman and
Keith Anderson and
Krishnamurthy Dvijotham and
Nicolas Heess and
Pushmeet Kohli},
title = {Rigorous Agent Evaluation: An Adversarial Approach to Uncover Catastrophic
Failures},
journal = {CoRR},
volume = {abs/1812.01647},
year = {2018},
url = {http://arxiv.org/abs/1812.01647},
eprinttype = {arXiv},
eprint = {1812.01647},
timestamp = {Tue, 01 Jan 2019 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-1812-01647.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/jmlr/HuangLGS17,
author = {Ruitong Huang and
Tor Lattimore and
Andr{\'{a}}s Gy{\"{o}}rgy and
Csaba Szepesv{\'{a}}ri},
title = {Following the Leader and Fast Rates in Online Linear Prediction: Curved
Constraint Sets and Other Regularities},
journal = {J. Mach. Learn. Res.},
volume = {18},
pages = {145:1--145:31},
year = {2017},
url = {http://jmlr.org/papers/v18/17-079.html},
timestamp = {Tue, 19 May 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/jmlr/HuangLGS17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aistats/KatariyaKSVW17,
author = {Sumeet Katariya and
Branislav Kveton and
Csaba Szepesv{\'{a}}ri and
Claire Vernade and
Zheng Wen},
editor = {Aarti Singh and
Xiaojin (Jerry) Zhu},
title = {Stochastic Rank-1 Bandits},
booktitle = {Proceedings of the 20th International Conference on Artificial Intelligence
and Statistics, {AISTATS} 2017, 20-22 April 2017, Fort Lauderdale,
FL, {USA}},
series = {Proceedings of Machine Learning Research},
volume = {54},
pages = {392--401},
publisher = {{PMLR}},
year = {2017},
url = {http://proceedings.mlr.press/v54/katariya17a.html},
timestamp = {Wed, 29 May 2019 08:41:44 +0200},
biburl = {https://dblp.org/rec/conf/aistats/KatariyaKSVW17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aistats/LattimoreS17,
author = {Tor Lattimore and
Csaba Szepesv{\'{a}}ri},
editor = {Aarti Singh and
Xiaojin (Jerry) Zhu},
title = {The End of Optimism? An Asymptotic Analysis of Finite-Armed Linear
Bandits},
booktitle = {Proceedings of the 20th International Conference on Artificial Intelligence
and Statistics, {AISTATS} 2017, 20-22 April 2017, Fort Lauderdale,
FL, {USA}},
series = {Proceedings of Machine Learning Research},
volume = {54},
pages = {728--737},
publisher = {{PMLR}},
year = {2017},
url = {http://proceedings.mlr.press/v54/lattimore17a.html},
timestamp = {Wed, 03 Apr 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/aistats/LattimoreS17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aistats/HanawalSS17,
author = {Manjesh Kumar Hanawal and
Csaba Szepesv{\'{a}}ri and
Venkatesh Saligrama},
editor = {Aarti Singh and
Xiaojin (Jerry) Zhu},
title = {Unsupervised Sequential Sensor Acquisition},
booktitle = {Proceedings of the 20th International Conference on Artificial Intelligence
and Statistics, {AISTATS} 2017, 20-22 April 2017, Fort Lauderdale,
FL, {USA}},
series = {Proceedings of Machine Learning Research},
volume = {54},
pages = {803--811},
publisher = {{PMLR}},
year = {2017},
url = {http://proceedings.mlr.press/v54/hanawal17a.html},
timestamp = {Wed, 03 Apr 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/aistats/HanawalSS17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/alt/HuangAS017,
author = {Ruitong Huang and
Mohammad M. Ajallooeian and
Csaba Szepesv{\'{a}}ri and
Martin M{\"{u}}ller},
editor = {Steve Hanneke and
Lev Reyzin},
title = {Structured Best Arm Identification with Fixed Confidence},
booktitle = {International Conference on Algorithmic Learning Theory, {ALT} 2017,
15-17 October 2017, Kyoto University, Kyoto, Japan},
series = {Proceedings of Machine Learning Research},
volume = {76},
pages = {593--616},
publisher = {{PMLR}},
year = {2017},
url = {http://proceedings.mlr.press/v76/huang17a.html},
timestamp = {Wed, 03 Apr 2019 18:17:23 +0200},
biburl = {https://dblp.org/rec/conf/alt/HuangAS017.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/alt/JoulaniGS17,
author = {Pooria Joulani and
Andr{\'{a}}s Gy{\"{o}}rgy and
Csaba Szepesv{\'{a}}ri},
editor = {Steve Hanneke and
Lev Reyzin},
title = {A Modular Analysis of Adaptive (Non-)Convex Optimization: Optimism,
Composite Objectives, and Variational Bounds},
booktitle = {International Conference on Algorithmic Learning Theory, {ALT} 2017,
15-17 October 2017, Kyoto University, Kyoto, Japan},
series = {Proceedings of Machine Learning Research},
volume = {76},
pages = {681--720},
publisher = {{PMLR}},
year = {2017},
url = {http://proceedings.mlr.press/v76/joulani17a.html},
timestamp = {Tue, 19 May 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/alt/JoulaniGS17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/ZoghiTGKSW17,
author = {Masrour Zoghi and
Tom{\'{a}}s Tunys and
Mohammad Ghavamzadeh and
Branislav Kveton and
Csaba Szepesv{\'{a}}ri and
Zheng Wen},
editor = {Doina Precup and
Yee Whye Teh},
title = {Online Learning to Rank in Stochastic Click Models},
booktitle = {Proceedings of the 34th International Conference on Machine Learning,
{ICML} 2017, Sydney, NSW, Australia, 6-11 August 2017},
series = {Proceedings of Machine Learning Research},
volume = {70},
pages = {4199--4208},
publisher = {{PMLR}},
year = {2017},
url = {http://proceedings.mlr.press/v70/zoghi17a.html},
timestamp = {Wed, 29 May 2019 08:41:45 +0200},
biburl = {https://dblp.org/rec/conf/icml/ZoghiTGKSW17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ijcai/KatariyaKSVW17,
author = {Sumeet Katariya and
Branislav Kveton and
Csaba Szepesv{\'{a}}ri and
Claire Vernade and
Zheng Wen},
editor = {Carles Sierra},
title = {Bernoulli Rank-1 Bandits for Click Feedback},
booktitle = {Proceedings of the Twenty-Sixth International Joint Conference on
Artificial Intelligence, {IJCAI} 2017, Melbourne, Australia, August
19-25, 2017},
pages = {2001--2007},
publisher = {ijcai.org},
year = {2017},
url = {https://doi.org/10.24963/ijcai.2017/278},
doi = {10.24963/IJCAI.2017/278},
timestamp = {Tue, 20 Aug 2019 16:16:54 +0200},
biburl = {https://dblp.org/rec/conf/ijcai/KatariyaKSVW17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/KaramiWSS17,
author = {Mahdi Karami and
Martha White and
Dale Schuurmans and
Csaba Szepesv{\'{a}}ri},
editor = {Isabelle Guyon and
Ulrike von Luxburg and
Samy Bengio and
Hanna M. Wallach and
Rob Fergus and
S. V. N. Vishwanathan and
Roman Garnett},
title = {Multi-view Matrix Factorization for Linear Dynamical System Estimation},
booktitle = {Advances in Neural Information Processing Systems 30: Annual Conference
on Neural Information Processing Systems 2017, December 4-9, 2017,
Long Beach, CA, {USA}},
pages = {7092--7101},
year = {2017},
url = {https://proceedings.neurips.cc/paper/2017/hash/c2964caac096f26db222cb325aa267cb-Abstract.html},
timestamp = {Thu, 21 Jan 2021 13:58:27 +0100},
biburl = {https://dblp.org/rec/conf/nips/KaramiWSS17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/HuangLGS17,
author = {Ruitong Huang and
Tor Lattimore and
Andr{\'{a}}s Gy{\"{o}}rgy and
Csaba Szepesv{\'{a}}ri},
title = {Following the Leader and Fast Rates in Linear Prediction: Curved Constraint
Sets and Other Regularities},
journal = {CoRR},
volume = {abs/1702.03040},
year = {2017},
url = {http://arxiv.org/abs/1702.03040},
eprinttype = {arXiv},
eprint = {1702.03040},
timestamp = {Tue, 19 May 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/HuangLGS17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/GhavamzadehKSTW17,
author = {Mohammad Ghavamzadeh and
Branislav Kveton and
Csaba Szepesv{\'{a}}ri and
Tom{\'{a}}s Tunys and
Zheng Wen and
Masrour Zoghi},
title = {Online Learning to Rank in Stochastic Click Models},
journal = {CoRR},
volume = {abs/1703.02527},
year = {2017},
url = {http://arxiv.org/abs/1703.02527},
eprinttype = {arXiv},
eprint = {1703.02527},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/GhavamzadehKSTW17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/KatariyaKSVW17,
author = {Sumeet Katariya and
Branislav Kveton and
Csaba Szepesv{\'{a}}ri and
Claire Vernade and
Zheng Wen},
title = {Bernoulli Rank-1 Bandits for Click Feedback},
journal = {CoRR},
volume = {abs/1703.06513},
year = {2017},
url = {http://arxiv.org/abs/1703.06513},
eprinttype = {arXiv},
eprint = {1703.06513},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/KatariyaKSVW17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/Lakshminarayanan17,
author = {Chandrashekar Lakshminarayanan and
Shalabh Bhatnagar and
Csaba Szepesv{\'{a}}ri},
title = {A Linearly Relaxed Approximate Linear Program for Markov Decision
Processes},
journal = {CoRR},
volume = {abs/1704.02544},
year = {2017},
url = {http://arxiv.org/abs/1704.02544},
eprinttype = {arXiv},
eprint = {1704.02544},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/Lakshminarayanan17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/HuangASM17,
author = {Ruitong Huang and
Mohammad M. Ajallooeian and
Csaba Szepesv{\'{a}}ri and
Martin M{\"{u}}ller},
title = {Structured Best Arm Identification with Fixed Confidence},
journal = {CoRR},
volume = {abs/1706.05198},
year = {2017},
url = {http://arxiv.org/abs/1706.05198},
eprinttype = {arXiv},
eprint = {1706.05198},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/HuangASM17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/Abou-MoustafaS17,
author = {Karim T. Abou{-}Moustafa and
Csaba Szepesv{\'{a}}ri},
title = {An a Priori Exponential Tail Bound for k-Folds Cross-Validation},
journal = {CoRR},
volume = {abs/1706.05801},
year = {2017},
url = {http://arxiv.org/abs/1706.05801},
eprinttype = {arXiv},
eprint = {1706.05801},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/Abou-MoustafaS17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/MaOSS17,
author = {Yao Ma and
Alex Olshevsky and
Venkatesh Saligrama and
Csaba Szepesv{\'{a}}ri},
title = {Crowdsourcing with Sparsely Interacting Workers},
journal = {CoRR},
volume = {abs/1706.06660},
year = {2017},
url = {http://arxiv.org/abs/1706.06660},
eprinttype = {arXiv},
eprint = {1706.06660},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/MaOSS17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1708-07367,
author = {Daniel J. Hsu and
Aryeh Kontorovich and
David A. Levin and
Yuval Peres and
Csaba Szepesv{\'{a}}ri},
title = {Mixing time estimation in reversible Markov chains from a single sample
path},
journal = {CoRR},
volume = {abs/1708.07367},
year = {2017},
url = {http://arxiv.org/abs/1708.07367},
eprinttype = {arXiv},
eprint = {1708.07367},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1708-07367.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1709-02726,
author = {Pooria Joulani and
Andr{\'{a}}s Gy{\"{o}}rgy and
Csaba Szepesv{\'{a}}ri},
title = {A Modular Analysis of Adaptive (Non-)Convex Optimization: Optimism,
Composite Objectives, and Variational Bounds},
journal = {CoRR},
volume = {abs/1709.02726},
year = {2017},
url = {http://arxiv.org/abs/1709.02726},
eprinttype = {arXiv},
eprint = {1709.02726},
timestamp = {Tue, 19 May 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1709-02726.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1709-04073,
author = {Chandrashekar Lakshminarayanan and
Csaba Szepesv{\'{a}}ri},
title = {Linear Stochastic Approximation: Constant Step-Size and Iterate Averaging},
journal = {CoRR},
volume = {abs/1709.04073},
year = {2017},
url = {http://arxiv.org/abs/1709.04073},
eprinttype = {arXiv},
eprint = {1709.04073},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1709-04073.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1709-06853,
author = {Ciara Pike{-}Burke and
Shipra Agrawal and
Csaba Szepesv{\'{a}}ri and
Steffen Gr{\"{u}}new{\"{a}}lder},
title = {Bandits with Delayed Anonymous Feedback},
journal = {CoRR},
volume = {abs/1709.06853},
year = {2017},
url = {http://arxiv.org/abs/1709.06853},
eprinttype = {arXiv},
eprint = {1709.06853},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1709-06853.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1712-04644,
author = {Branislav Kveton and
Csaba Szepesv{\'{a}}ri and
Anup Rao and
Zheng Wen and
Yasin Abbasi{-}Yadkori and
S. Muthukrishnan},
title = {Stochastic Low-Rank Bandits},
journal = {CoRR},
volume = {abs/1712.04644},
year = {2017},
url = {http://arxiv.org/abs/1712.04644},
eprinttype = {arXiv},
eprint = {1712.04644},
timestamp = {Mon, 10 May 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1712-04644.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/jmlr/FarahmandGSM16,
author = {Amir{-}massoud Farahmand and
Mohammad Ghavamzadeh and
Csaba Szepesv{\'{a}}ri and
Shie Mannor},
title = {Regularized Policy Iteration with Nonparametric Function Spaces},
journal = {J. Mach. Learn. Res.},
volume = {17},
pages = {139:1--139:66},
year = {2016},
url = {http://jmlr.org/papers/v17/13-016.html},
timestamp = {Wed, 10 Jul 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/jmlr/FarahmandGSM16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/JoulaniGS16,
author = {Pooria Joulani and
Andr{\'{a}}s Gy{\"{o}}rgy and
Csaba Szepesv{\'{a}}ri},
editor = {Dale Schuurmans and
Michael P. Wellman},
title = {Delay-Tolerant Online Convex Optimization: Unified Analysis and Adaptive-Gradient
Algorithms},
booktitle = {Proceedings of the Thirtieth {AAAI} Conference on Artificial Intelligence,
February 12-17, 2016, Phoenix, Arizona, {USA}},
pages = {1744--1750},
publisher = {{AAAI} Press},
year = {2016},
url = {https://doi.org/10.1609/aaai.v30i1.10320},
doi = {10.1609/AAAI.V30I1.10320},
timestamp = {Mon, 04 Sep 2023 15:08:28 +0200},
biburl = {https://dblp.org/rec/conf/aaai/JoulaniGS16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/LeverSSS16,
author = {Guy Lever and
John Shawe{-}Taylor and
Ronnie Stafford and
Csaba Szepesv{\'{a}}ri},
editor = {Dale Schuurmans and
Michael P. Wellman},
title = {Compressed Conditional Mean Embeddings for Model-Based Reinforcement
Learning},
booktitle = {Proceedings of the Thirtieth {AAAI} Conference on Artificial Intelligence,
February 12-17, 2016, Phoenix, Arizona, {USA}},
pages = {1779--1787},
publisher = {{AAAI} Press},
year = {2016},
url = {https://doi.org/10.1609/aaai.v30i1.10304},
doi = {10.1609/AAAI.V30I1.10304},
timestamp = {Mon, 04 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/aaai/LeverSSS16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aistats/HuAGS16,
author = {Xiaowei Hu and
Prashanth L. A. and
Andr{\'{a}}s Gy{\"{o}}rgy and
Csaba Szepesv{\'{a}}ri},
editor = {Arthur Gretton and
Christian C. Robert},
title = {(Bandit) Convex Optimization with Biased Noisy Gradient Oracles},
booktitle = {Proceedings of the 19th International Conference on Artificial Intelligence
and Statistics, {AISTATS} 2016, Cadiz, Spain, May 9-11, 2016},
series = {{JMLR} Workshop and Conference Proceedings},
volume = {51},
pages = {819--828},
publisher = {JMLR.org},
year = {2016},
url = {http://proceedings.mlr.press/v51/hu16b.html},
timestamp = {Tue, 15 Feb 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/aistats/HuAGS16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/KatariyaKSW16,
author = {Sumeet Katariya and
Branislav Kveton and
Csaba Szepesv{\'{a}}ri and
Zheng Wen},
editor = {Maria{-}Florina Balcan and
Kilian Q. Weinberger},
title = {{DCM} Bandits: Learning to Rank with Multiple Clicks},
booktitle = {Proceedings of the 33nd International Conference on Machine Learning,
{ICML} 2016, New York City, NY, USA, June 19-24, 2016},
series = {{JMLR} Workshop and Conference Proceedings},
volume = {48},
pages = {1215--1224},
publisher = {JMLR.org},
year = {2016},
url = {http://proceedings.mlr.press/v48/katariya16.html},
timestamp = {Wed, 29 May 2019 08:41:46 +0200},
biburl = {https://dblp.org/rec/conf/icml/KatariyaKSW16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/WuSLS16,
author = {Yifan Wu and
Roshan Shariff and
Tor Lattimore and
Csaba Szepesv{\'{a}}ri},
editor = {Maria{-}Florina Balcan and
Kilian Q. Weinberger},
title = {Conservative Bandits},
booktitle = {Proceedings of the 33nd International Conference on Machine Learning,
{ICML} 2016, New York City, NY, USA, June 19-24, 2016},
series = {{JMLR} Workshop and Conference Proceedings},
volume = {48},
pages = {1254--1262},
publisher = {JMLR.org},
year = {2016},
url = {http://proceedings.mlr.press/v48/wu16.html},
timestamp = {Wed, 29 May 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/WuSLS16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/AJFMS16,
author = {Prashanth L. A. and
Cheng Jie and
Michael C. Fu and
Steven I. Marcus and
Csaba Szepesv{\'{a}}ri},
editor = {Maria{-}Florina Balcan and
Kilian Q. Weinberger},
title = {Cumulative Prospect Theory Meets Reinforcement Learning: Prediction
and Control},
booktitle = {Proceedings of the 33nd International Conference on Machine Learning,
{ICML} 2016, New York City, NY, USA, June 19-24, 2016},
series = {{JMLR} Workshop and Conference Proceedings},
volume = {48},
pages = {1406--1415},
publisher = {JMLR.org},
year = {2016},
url = {http://proceedings.mlr.press/v48/la16.html},
timestamp = {Wed, 20 Nov 2019 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icml/AJFMS16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/GyorgyS16,
author = {Andr{\'{a}}s Gy{\"{o}}rgy and
Csaba Szepesv{\'{a}}ri},
editor = {Maria{-}Florina Balcan and
Kilian Q. Weinberger},
title = {Shifting Regret, Mirror Descent, and Matrices},
booktitle = {Proceedings of the 33nd International Conference on Machine Learning,
{ICML} 2016, New York City, NY, USA, June 19-24, 2016},
series = {{JMLR} Workshop and Conference Proceedings},
volume = {48},
pages = {2943--2951},
publisher = {JMLR.org},
year = {2016},
url = {http://proceedings.mlr.press/v48/gyorgy16.html},
timestamp = {Tue, 19 May 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/GyorgyS16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/HuangLGS16,
author = {Ruitong Huang and
Tor Lattimore and
Andr{\'{a}}s Gy{\"{o}}rgy and
Csaba Szepesv{\'{a}}ri},
editor = {Daniel D. Lee and
Masashi Sugiyama and
Ulrike von Luxburg and
Isabelle Guyon and
Roman Garnett},
title = {Following the Leader and Fast Rates in Linear Prediction: Curved Constraint
Sets and Other Regularities},
booktitle = {Advances in Neural Information Processing Systems 29: Annual Conference
on Neural Information Processing Systems 2016, December 5-10, 2016,
Barcelona, Spain},
pages = {4970--4978},
year = {2016},
url = {https://proceedings.neurips.cc/paper/2016/hash/55a988dfb00a914717b3000a3374694c-Abstract.html},
timestamp = {Mon, 16 May 2022 15:41:51 +0200},
biburl = {https://dblp.org/rec/conf/nips/HuangLGS16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/ShaloudegiGSX16,
author = {Kiarash Shaloudegi and
Andr{\'{a}}s Gy{\"{o}}rgy and
Csaba Szepesv{\'{a}}ri and
Wilsun Xu},
editor = {Daniel D. Lee and
Masashi Sugiyama and
Ulrike von Luxburg and
Isabelle Guyon and
Roman Garnett},
title = {{SDP} Relaxation with Randomized Rounding for Energy Disaggregation},
booktitle = {Advances in Neural Information Processing Systems 29: Annual Conference
on Neural Information Processing Systems 2016, December 5-10, 2016,
Barcelona, Spain},
pages = {4979--4987},
year = {2016},
url = {https://proceedings.neurips.cc/paper/2016/hash/4de754248c196c85ee4fbdcee89179bd-Abstract.html},
timestamp = {Thu, 21 Jan 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/ShaloudegiGSX16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/KatariyaKSW16,
author = {Sumeet Katariya and
Branislav Kveton and
Csaba Szepesv{\'{a}}ri and
Zheng Wen},
title = {{DCM} Bandits: Learning to Rank with Multiple Clicks},
journal = {CoRR},
volume = {abs/1602.03146},
year = {2016},
url = {http://arxiv.org/abs/1602.03146},
eprinttype = {arXiv},
eprint = {1602.03146},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/KatariyaKSW16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/WuSLS16,
author = {Yifan Wu and
Roshan Shariff and
Tor Lattimore and
Csaba Szepesv{\'{a}}ri},
title = {Conservative Bandits},
journal = {CoRR},
volume = {abs/1602.04282},
year = {2016},
url = {http://arxiv.org/abs/1602.04282},
eprinttype = {arXiv},
eprint = {1602.04282},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/WuSLS16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/PiresS16,
author = {Bernardo {\'{A}}vila Pires and
Csaba Szepesv{\'{a}}ri},
title = {Policy Error Bounds for Model-Based Reinforcement Learning with Factored
Linear Models},
journal = {CoRR},
volume = {abs/1602.06346},
year = {2016},
url = {http://arxiv.org/abs/1602.06346},
eprinttype = {arXiv},
eprint = {1602.06346},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/PiresS16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/KatariyaKSVW16,
author = {Sumeet Katariya and
Branislav Kveton and
Csaba Szepesv{\'{a}}ri and
Claire Vernade and
Zheng Wen},
title = {Stochastic Rank-1 Bandits},
journal = {CoRR},
volume = {abs/1608.03023},
year = {2016},
url = {http://arxiv.org/abs/1608.03023},
eprinttype = {arXiv},
eprint = {1608.03023},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/KatariyaKSVW16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/BalazsGS16,
author = {G{\'{a}}bor Bal{\'{a}}zs and
Andr{\'{a}}s Gy{\"{o}}rgy and
Csaba Szepesv{\'{a}}ri},
title = {Chaining Bounds for Empirical Risk Minimization},
journal = {CoRR},
volume = {abs/1609.01872},
year = {2016},
url = {http://arxiv.org/abs/1609.01872},
eprinttype = {arXiv},
eprint = {1609.01872},
timestamp = {Mon, 25 Mar 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/BalazsGS16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/BalazsGS16a,
author = {G{\'{a}}bor Bal{\'{a}}zs and
Andr{\'{a}}s Gy{\"{o}}rgy and
Csaba Szepesv{\'{a}}ri},
title = {Max-affine estimators for convex stochastic programming},
journal = {CoRR},
volume = {abs/1609.06331},
year = {2016},
url = {http://arxiv.org/abs/1609.06331},
eprinttype = {arXiv},
eprint = {1609.06331},
timestamp = {Mon, 25 Mar 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/BalazsGS16a.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/PiresS16a,
author = {Bernardo {\'{A}}vila Pires and
Csaba Szepesv{\'{a}}ri},
title = {Multiclass Classification Calibration Functions},
journal = {CoRR},
volume = {abs/1609.06385},
year = {2016},
url = {http://arxiv.org/abs/1609.06385},
eprinttype = {arXiv},
eprint = {1609.06385},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/PiresS16a.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/HuAGS16,
author = {Xiaowei Hu and
Prashanth L. A. and
Andr{\'{a}}s Gy{\"{o}}rgy and
Csaba Szepesv{\'{a}}ri},
title = {(Bandit) Convex Optimization with Biased Noisy Gradient Oracles},
journal = {CoRR},
volume = {abs/1609.07087},
year = {2016},
url = {http://arxiv.org/abs/1609.07087},
eprinttype = {arXiv},
eprint = {1609.07087},
timestamp = {Tue, 15 Feb 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/HuAGS16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/LattimoreS16,
author = {Tor Lattimore and
Csaba Szepesv{\'{a}}ri},
title = {The End of Optimism? An Asymptotic Analysis of Finite-Armed Linear
Bandits},
journal = {CoRR},
volume = {abs/1610.04491},
year = {2016},
url = {http://arxiv.org/abs/1610.04491},
eprinttype = {arXiv},
eprint = {1610.04491},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/LattimoreS16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/HanawalSS16,
author = {Manjesh Kumar Hanawal and
Csaba Szepesv{\'{a}}ri and
Venkatesh Saligrama},
title = {Sequential Learning without Feedback},
journal = {CoRR},
volume = {abs/1610.05394},
year = {2016},
url = {http://arxiv.org/abs/1610.05394},
eprinttype = {arXiv},
eprint = {1610.05394},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/HanawalSS16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/ShaloudegiGSX16,
author = {Kiarash Shaloudegi and
Andr{\'{a}}s Gy{\"{o}}rgy and
Csaba Szepesv{\'{a}}ri and
Wilsun Xu},
title = {{SDP} Relaxation with Randomized Rounding for Energy Disaggregation},
journal = {CoRR},
volume = {abs/1610.09491},
year = {2016},
url = {http://arxiv.org/abs/1610.09491},
eprinttype = {arXiv},
eprint = {1610.09491},
timestamp = {Tue, 19 May 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/ShaloudegiGSX16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/BardNSB15,
author = {Nolan Bard and
Deon Nicholas and
Csaba Szepesv{\'{a}}ri and
Michael Bowling},
editor = {Sam Ganzfried},
title = {Decision-Theoretic Clustering of Strategies},
booktitle = {Computer Poker and Imperfect Information, Papers from the 2015 {AAAI}
Workshop, Austin, Texas, USA, January 26, 2015},
series = {{AAAI} Technical Report},
volume = {{WS-15-07}},
publisher = {{AAAI} Press},
year = {2015},
url = {http://aaai.org/ocs/index.php/WS/AAAIW15/paper/view/10201},
timestamp = {Tue, 05 Sep 2023 08:59:27 +0200},
biburl = {https://dblp.org/rec/conf/aaai/BardNSB15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/PiresS15,
author = {Bernardo {\'{A}}vila Pires and
Csaba Szepesv{\'{a}}ri},
editor = {Michael Bowling and
Marc G. Bellemare and
Erik Talvitie and
Joel Veness and
Marlos C. Machado},
title = {Pathological Effects of Variance on Classification-Based Policy Iteration},
booktitle = {Learning for General Competency in Video Games, Papers from the 2015
{AAAI} Workshop, Austin, Texas, USA, January 26, 2015},
series = {{AAAI} Technical Report},
volume = {{WS-15-10}},
publisher = {{AAAI} Press},
year = {2015},
url = {http://aaai.org/ocs/index.php/WS/AAAIW15/paper/view/10098},
timestamp = {Tue, 05 Sep 2023 08:59:27 +0200},
biburl = {https://dblp.org/rec/conf/aaai/PiresS15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aistats/BalazsGS15,
author = {G{\'{a}}bor Bal{\'{a}}zs and
Andr{\'{a}}s Gy{\"{o}}rgy and
Csaba Szepesv{\'{a}}ri},
editor = {Guy Lebanon and
S. V. N. Vishwanathan},
title = {Near-optimal max-affine estimators for convex regression},
booktitle = {Proceedings of the Eighteenth International Conference on Artificial
Intelligence and Statistics, {AISTATS} 2015, San Diego, California,
USA, May 9-12, 2015},
series = {{JMLR} Workshop and Conference Proceedings},
volume = {38},
publisher = {JMLR.org},
year = {2015},
url = {http://proceedings.mlr.press/v38/balazs15.html},
timestamp = {Mon, 25 Mar 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/aistats/BalazsGS15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aistats/KvetonWAS15,
author = {Branislav Kveton and
Zheng Wen and
Azin Ashkan and
Csaba Szepesv{\'{a}}ri},
editor = {Guy Lebanon and
S. V. N. Vishwanathan},
title = {Tight Regret Bounds for Stochastic Combinatorial Semi-Bandits},
booktitle = {Proceedings of the Eighteenth International Conference on Artificial
Intelligence and Statistics, {AISTATS} 2015, San Diego, California,
USA, May 9-12, 2015},
series = {{JMLR} Workshop and Conference Proceedings},
volume = {38},
publisher = {JMLR.org},
year = {2015},
url = {http://proceedings.mlr.press/v38/kveton15.html},
timestamp = {Wed, 29 May 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/aistats/KvetonWAS15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aistats/LiMS15,
author = {Lihong Li and
R{\'{e}}mi Munos and
Csaba Szepesv{\'{a}}ri},
editor = {Guy Lebanon and
S. V. N. Vishwanathan},
title = {Toward Minimax Off-policy Value Estimation},
booktitle = {Proceedings of the Eighteenth International Conference on Artificial
Intelligence and Statistics, {AISTATS} 2015, San Diego, California,
USA, May 9-12, 2015},
series = {{JMLR} Workshop and Conference Proceedings},
volume = {38},
publisher = {JMLR.org},
year = {2015},
url = {http://proceedings.mlr.press/v38/li15b.html},
timestamp = {Wed, 29 May 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/aistats/LiMS15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aistats/ShariffGS15,
author = {Roshan Shariff and
Andr{\'{a}}s Gy{\"{o}}rgy and
Csaba Szepesv{\'{a}}ri},
editor = {Guy Lebanon and
S. V. N. Vishwanathan},
title = {Exploiting Symmetries to Construct Efficient {MCMC} Algorithms With
an Application to {SLAM}},
booktitle = {Proceedings of the Eighteenth International Conference on Artificial
Intelligence and Statistics, {AISTATS} 2015, San Diego, California,
USA, May 9-12, 2015},
series = {{JMLR} Workshop and Conference Proceedings},
volume = {38},
publisher = {JMLR.org},
year = {2015},
url = {http://proceedings.mlr.press/v38/shariff15.html},
timestamp = {Tue, 19 May 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/aistats/ShariffGS15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/atal/BardNSB15,
author = {Nolan Bard and
Deon Nicholas and
Csaba Szepesv{\'{a}}ri and
Michael H. Bowling},
editor = {Gerhard Weiss and
Pinar Yolum and
Rafael H. Bordini and
Edith Elkind},
title = {Decision-theoretic Clustering of Strategies},
booktitle = {Proceedings of the 2015 International Conference on Autonomous Agents
and Multiagent Systems, {AAMAS} 2015, Istanbul, Turkey, May 4-8, 2015},
pages = {17--25},
publisher = {{ACM}},
year = {2015},
url = {http://dl.acm.org/citation.cfm?id=2772886},
timestamp = {Tue, 08 Mar 2022 10:12:47 +0100},
biburl = {https://dblp.org/rec/conf/atal/BardNSB15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/KvetonSWA15,
author = {Branislav Kveton and
Csaba Szepesv{\'{a}}ri and
Zheng Wen and
Azin Ashkan},
editor = {Francis R. Bach and
David M. Blei},
title = {Cascading Bandits: Learning to Rank in the Cascade Model},
booktitle = {Proceedings of the 32nd International Conference on Machine Learning,
{ICML} 2015, Lille, France, 6-11 July 2015},
series = {{JMLR} Workshop and Conference Proceedings},
volume = {37},
pages = {767--776},
publisher = {JMLR.org},
year = {2015},
url = {http://proceedings.mlr.press/v37/kveton15.html},
timestamp = {Wed, 29 May 2019 08:41:45 +0200},
biburl = {https://dblp.org/rec/conf/icml/KvetonSWA15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/WuGS15,
author = {Yifan Wu and
Andr{\'{a}}s Gy{\"{o}}rgy and
Csaba Szepesv{\'{a}}ri},
editor = {Francis R. Bach and
David M. Blei},
title = {On Identifying Good Options under Combinatorially Structured Feedback
in Finite Noisy Environments},
booktitle = {Proceedings of the 32nd International Conference on Machine Learning,
{ICML} 2015, Lille, France, 6-11 July 2015},
series = {{JMLR} Workshop and Conference Proceedings},
volume = {37},
pages = {1283--1291},
publisher = {JMLR.org},
year = {2015},
url = {http://proceedings.mlr.press/v37/wub15.html},
timestamp = {Tue, 19 May 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/WuGS15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/HuangGS15,
author = {Ruitong Huang and
Andr{\'{a}}s Gy{\"{o}}rgy and
Csaba Szepesv{\'{a}}ri},
editor = {Francis R. Bach and
David M. Blei},
title = {Deterministic Independent Component Analysis},
booktitle = {Proceedings of the 32nd International Conference on Machine Learning,
{ICML} 2015, Lille, France, 6-11 July 2015},
series = {{JMLR} Workshop and Conference Proceedings},
volume = {37},
pages = {2521--2530},
publisher = {JMLR.org},
year = {2015},
url = {http://proceedings.mlr.press/v37/huangb15.html},
timestamp = {Tue, 19 May 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/HuangGS15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ijcai/JoulaniGS15,
author = {Pooria Joulani and
Andr{\'{a}}s Gy{\"{o}}rgy and
Csaba Szepesv{\'{a}}ri},
editor = {Qiang Yang and
Michael J. Wooldridge},
title = {Fast Cross-Validation for Incremental Learning},
booktitle = {Proceedings of the Twenty-Fourth International Joint Conference on
Artificial Intelligence, {IJCAI} 2015, Buenos Aires, Argentina, July
25-31, 2015},
pages = {3597--3604},
publisher = {{AAAI} Press},
year = {2015},
url = {http://ijcai.org/Abstract/15/506},
timestamp = {Tue, 19 May 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/ijcai/JoulaniGS15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/LattimoreCS15,
author = {Tor Lattimore and
Koby Crammer and
Csaba Szepesv{\'{a}}ri},
editor = {Corinna Cortes and
Neil D. Lawrence and
Daniel D. Lee and
Masashi Sugiyama and
Roman Garnett},
title = {Linear Multi-Resource Allocation with Semi-Bandit Feedback},
booktitle = {Advances in Neural Information Processing Systems 28: Annual Conference
on Neural Information Processing Systems 2015, December 7-12, 2015,
Montreal, Quebec, Canada},
pages = {964--972},
year = {2015},
url = {https://proceedings.neurips.cc/paper/2015/hash/851ddf5058cf22df63d3344ad89919cf-Abstract.html},
timestamp = {Mon, 16 May 2022 15:41:51 +0200},
biburl = {https://dblp.org/rec/conf/nips/LattimoreCS15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/WuGS15,
author = {Yifan Wu and
Andr{\'{a}}s Gy{\"{o}}rgy and
Csaba Szepesv{\'{a}}ri},
editor = {Corinna Cortes and
Neil D. Lawrence and
Daniel D. Lee and
Masashi Sugiyama and
Roman Garnett},
title = {Online Learning with Gaussian Payoffs and Side Observations},
booktitle = {Advances in Neural Information Processing Systems 28: Annual Conference
on Neural Information Processing Systems 2015, December 7-12, 2015,
Montreal, Quebec, Canada},
pages = {1360--1368},
year = {2015},
url = {https://proceedings.neurips.cc/paper/2015/hash/8e82ab7243b7c66d768f1b8ce1c967eb-Abstract.html},
timestamp = {Thu, 21 Jan 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/WuGS15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/KvetonWAS15,
author = {Branislav Kveton and
Zheng Wen and
Azin Ashkan and
Csaba Szepesv{\'{a}}ri},
editor = {Corinna Cortes and
Neil D. Lawrence and
Daniel D. Lee and
Masashi Sugiyama and
Roman Garnett},
title = {Combinatorial Cascading Bandits},
booktitle = {Advances in Neural Information Processing Systems 28: Annual Conference
on Neural Information Processing Systems 2015, December 7-12, 2015,
Montreal, Quebec, Canada},
pages = {1450--1458},
year = {2015},
url = {https://proceedings.neurips.cc/paper/2015/hash/1f50893f80d6830d62765ffad7721742-Abstract.html},
timestamp = {Thu, 21 Jan 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/KvetonWAS15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/HsuKS15,
author = {Daniel J. Hsu and
Aryeh Kontorovich and
Csaba Szepesv{\'{a}}ri},
editor = {Corinna Cortes and
Neil D. Lawrence and
Daniel D. Lee and
Masashi Sugiyama and
Roman Garnett},
title = {Mixing Time Estimation in Reversible Markov Chains from a Single Sample
Path},
booktitle = {Advances in Neural Information Processing Systems 28: Annual Conference
on Neural Information Processing Systems 2015, December 7-12, 2015,
Montreal, Quebec, Canada},
pages = {1459--1467},
year = {2015},
url = {https://proceedings.neurips.cc/paper/2015/hash/7ce3284b743aefde80ffd9aec500e085-Abstract.html},
timestamp = {Thu, 21 Jan 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/HsuKS15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/uai/Abbasi-YadkoriS15,
author = {Yasin Abbasi{-}Yadkori and
Csaba Szepesv{\'{a}}ri},
editor = {Marina Meila and
Tom Heskes},
title = {Bayesian Optimal Control of Smoothly Parameterized Systems},
booktitle = {Proceedings of the Thirty-First Conference on Uncertainty in Artificial
Intelligence, {UAI} 2015, July 12-16, 2015, Amsterdam, The Netherlands},
pages = {1--11},
publisher = {{AUAI} Press},
year = {2015},
url = {http://auai.org/uai2015/proceedings/papers/271.pdf},
timestamp = {Thu, 12 Mar 2020 11:31:09 +0100},
biburl = {https://dblp.org/rec/conf/uai/Abbasi-YadkoriS15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/KvetonSWA15,
author = {Branislav Kveton and
Csaba Szepesv{\'{a}}ri and
Zheng Wen and
Azin Ashkan},
title = {Cascading Bandits},
journal = {CoRR},
volume = {abs/1502.02763},
year = {2015},
url = {http://arxiv.org/abs/1502.02763},
eprinttype = {arXiv},
eprint = {1502.02763},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/KvetonSWA15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/HsuKS15,
author = {Daniel J. Hsu and
Aryeh Kontorovich and
Csaba Szepesv{\'{a}}ri},
title = {Mixing Time Estimation in Reversible Markov Chains from a Single Sample
Path},
journal = {CoRR},
volume = {abs/1506.02903},
year = {2015},
url = {http://arxiv.org/abs/1506.02903},
eprinttype = {arXiv},
eprint = {1506.02903},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/HsuKS15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/JoulaniGS15,
author = {Pooria Joulani and
Andr{\'{a}}s Gy{\"{o}}rgy and
Csaba Szepesv{\'{a}}ri},
title = {Fast Cross-Validation for Incremental Learning},
journal = {CoRR},
volume = {abs/1507.00066},
year = {2015},
url = {http://arxiv.org/abs/1507.00066},
eprinttype = {arXiv},
eprint = {1507.00066},
timestamp = {Tue, 19 May 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/JoulaniGS15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/KvetonWAS15,
author = {Branislav Kveton and
Zheng Wen and
Azin Ashkan and
Csaba Szepesv{\'{a}}ri},
title = {Combinatorial Cascading Bandits},
journal = {CoRR},
volume = {abs/1507.04208},
year = {2015},
url = {http://arxiv.org/abs/1507.04208},
eprinttype = {arXiv},
eprint = {1507.04208},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/KvetonWAS15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/WuGS15,
author = {Yifan Wu and
Andr{\'{a}}s Gy{\"{o}}rgy and
Csaba Szepesv{\'{a}}ri},
title = {Online Learning with Gaussian Payoffs and Side Observations},
journal = {CoRR},
volume = {abs/1510.08108},
year = {2015},
url = {http://arxiv.org/abs/1510.08108},
eprinttype = {arXiv},
eprint = {1510.08108},
timestamp = {Tue, 19 May 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/WuGS15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/HuangXSS15,
author = {Ruitong Huang and
Bing Xu and
Dale Schuurmans and
Csaba Szepesv{\'{a}}ri},
title = {Learning with a Strong Adversary},
journal = {CoRR},
volume = {abs/1511.03034},
year = {2015},
url = {http://arxiv.org/abs/1511.03034},
eprinttype = {arXiv},
eprint = {1511.03034},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/HuangXSS15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/mor/BartokFPRS14,
author = {G{\'{a}}bor Bart{\'{o}}k and
Dean P. Foster and
D{\'{a}}vid P{\'{a}}l and
Alexander Rakhlin and
Csaba Szepesv{\'{a}}ri},
title = {Partial Monitoring - Classification, Regret Bounds, and Algorithms},
journal = {Math. Oper. Res.},
volume = {39},
number = {4},
pages = {967--997},
year = {2014},
url = {https://doi.org/10.1287/moor.2014.0663},
doi = {10.1287/MOOR.2014.0663},
timestamp = {Sun, 28 May 2017 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/mor/BartokFPRS14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tac/NeuGSA14,
author = {Gergely Neu and
Andr{\'{a}}s Gy{\"{o}}rgy and
Csaba Szepesv{\'{a}}ri and
Andr{\'{a}}s Antos},
title = {Online Markov Decision Processes Under Bandit Feedback},
journal = {{IEEE} Trans. Autom. Control.},
volume = {59},
number = {3},
pages = {676--691},
year = {2014},
url = {https://doi.org/10.1109/TAC.2013.2292137},
doi = {10.1109/TAC.2013.2292137},
timestamp = {Mon, 26 Oct 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/tac/NeuGSA14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tcs/KivinenSZ14,
author = {Jyrki Kivinen and
Csaba Szepesv{\'{a}}ri and
Thomas Zeugmann},
title = {Guest Editors' introduction},
journal = {Theor. Comput. Sci.},
volume = {519},
pages = {1--3},
year = {2014},
url = {https://doi.org/10.1016/j.tcs.2013.09.018},
doi = {10.1016/J.TCS.2013.09.018},
timestamp = {Wed, 17 Feb 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/tcs/KivinenSZ14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tsp/LeSZ14,
author = {Thanh Le and
Csaba Szepesv{\'{a}}ri and
Rong Zheng},
title = {Sequential Learning for Multi-Channel Wireless Network Monitoring
With Channel Switching Costs},
journal = {{IEEE} Trans. Signal Process.},
volume = {62},
number = {22},
pages = {5919--5929},
year = {2014},
url = {https://doi.org/10.1109/TSP.2014.2357779},
doi = {10.1109/TSP.2014.2357779},
timestamp = {Sat, 18 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/tsp/LeSZ14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/adprl/YaoSPZ14,
author = {Hengshuai Yao and
Csaba Szepesv{\'{a}}ri and
Bernardo {\'{A}}vila Pires and
Xinhua Zhang},
title = {Pseudo-MDPs and factored linear action models},
booktitle = {2014 {IEEE} Symposium on Adaptive Dynamic Programming and Reinforcement
Learning, {ADPRL} 2014, Orlando, FL, USA, December 9-12, 2014},
pages = {1--9},
publisher = {{IEEE}},
year = {2014},
url = {https://doi.org/10.1109/ADPRL.2014.7010633},
doi = {10.1109/ADPRL.2014.7010633},
timestamp = {Wed, 16 Oct 2019 14:14:48 +0200},
biburl = {https://dblp.org/rec/conf/adprl/YaoSPZ14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aistats/HuangS14,
author = {Ruitong Huang and
Csaba Szepesv{\'{a}}ri},
title = {A Finite-Sample Generalization Bound for Semiparametric Regression:
Partially Linear Models},
booktitle = {Proceedings of the Seventeenth International Conference on Artificial
Intelligence and Statistics, {AISTATS} 2014, Reykjavik, Iceland, April
22-25, 2014},
series = {{JMLR} Workshop and Conference Proceedings},
volume = {33},
pages = {402--410},
publisher = {JMLR.org},
year = {2014},
url = {http://proceedings.mlr.press/v33/huang14.html},
timestamp = {Wed, 29 May 2019 08:41:44 +0200},
biburl = {https://dblp.org/rec/conf/aistats/HuangS14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/alt/LattimoreGS14,
author = {Tor Lattimore and
Andr{\'{a}}s Gy{\"{o}}rgy and
Csaba Szepesv{\'{a}}ri},
editor = {Peter Auer and
Alexander Clark and
Thomas Zeugmann and
Sandra Zilles},
title = {On Learning the Optimal Waiting Time},
booktitle = {Algorithmic Learning Theory - 25th International Conference, {ALT}
2014, Bled, Slovenia, October 8-10, 2014. Proceedings},
series = {Lecture Notes in Computer Science},
volume = {8776},
pages = {200--214},
publisher = {Springer},
year = {2014},
url = {https://doi.org/10.1007/978-3-319-11662-4\_15},
doi = {10.1007/978-3-319-11662-4\_15},
timestamp = {Sun, 25 Oct 2020 22:46:29 +0100},
biburl = {https://dblp.org/rec/conf/alt/LattimoreGS14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/DickGS14,
author = {Travis Dick and
Andr{\'{a}}s Gy{\"{o}}rgy and
Csaba Szepesv{\'{a}}ri},
title = {Online Learning in Markov Decision Processes with Changing Cost Sequences},
booktitle = {Proceedings of the 31th International Conference on Machine Learning,
{ICML} 2014, Beijing, China, 21-26 June 2014},
series = {{JMLR} Workshop and Conference Proceedings},
volume = {32},
pages = {512--520},
publisher = {JMLR.org},
year = {2014},
url = {http://proceedings.mlr.press/v32/dick14.html},
timestamp = {Tue, 19 May 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/DickGS14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/NeufeldGSS14,
author = {James Neufeld and
Andr{\'{a}}s Gy{\"{o}}rgy and
Csaba Szepesv{\'{a}}ri and
Dale Schuurmans},
title = {Adaptive Monte Carlo via Bandit Allocation},
booktitle = {Proceedings of the 31th International Conference on Machine Learning,
{ICML} 2014, Beijing, China, 21-26 June 2014},
series = {{JMLR} Workshop and Conference Proceedings},
volume = {32},
pages = {1944--1952},
publisher = {JMLR.org},
year = {2014},
url = {http://proceedings.mlr.press/v32/neufeld14.html},
timestamp = {Tue, 19 May 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/NeufeldGSS14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/isaim/HuangS14,
author = {Ruitong Huang and
Csaba Szepesv{\'{a}}ri},
title = {Generalization Bounds for Partially Linear Models},
booktitle = {International Symposium on Artificial Intelligence and Mathematics,
{ISAIM} 2014, Fort Lauderdale, FL, USA, January 6-8, 2014},
year = {2014},
url = {http://www.cs.uic.edu/pub/Isaim2014/WebPreferences/ISAIM2014\_ML\_Huang\_Szepesvari.pdf},
timestamp = {Wed, 20 Mar 2024 17:48:47 +0100},
biburl = {https://dblp.org/rec/conf/isaim/HuangS14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/YaoSSMB14,
author = {Hengshuai Yao and
Csaba Szepesv{\'{a}}ri and
Richard S. Sutton and
Joseph Modayil and
Shalabh Bhatnagar},
editor = {Zoubin Ghahramani and
Max Welling and
Corinna Cortes and
Neil D. Lawrence and
Kilian Q. Weinberger},
title = {Universal Option Models},
booktitle = {Advances in Neural Information Processing Systems 27: Annual Conference
on Neural Information Processing Systems 2014, December 8-13 2014,
Montreal, Quebec, Canada},
pages = {990--998},
year = {2014},
url = {https://proceedings.neurips.cc/paper/2014/hash/996a7fa078cc36c46d02f9af3bef918b-Abstract.html},
timestamp = {Mon, 16 May 2022 15:41:51 +0200},
biburl = {https://dblp.org/rec/conf/nips/YaoSSMB14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/uai/LattimoreCS14,
author = {Tor Lattimore and
Koby Crammer and
Csaba Szepesv{\'{a}}ri},
editor = {Nevin L. Zhang and
Jin Tian},
title = {Optimal Resource Allocation with Semi-Bandit Feedback},
booktitle = {Proceedings of the Thirtieth Conference on Uncertainty in Artificial
Intelligence, {UAI} 2014, Quebec City, Quebec, Canada, July 23-27,
2014},
pages = {477--486},
publisher = {{AUAI} Press},
year = {2014},
url = {https://dslpitt.org/uai/displayArticleDetails.jsp?mmnu=1\&\#38;smnu=2\&\#38;article\_id=2483\&\#38;proceeding\_id=30},
timestamp = {Wed, 03 Feb 2021 11:09:27 +0100},
biburl = {https://dblp.org/rec/conf/uai/LattimoreCS14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@proceedings{DBLP:conf/colt/2014,
editor = {Maria{-}Florina Balcan and
Vitaly Feldman and
Csaba Szepesv{\'{a}}ri},
title = {Proceedings of The 27th Conference on Learning Theory, {COLT} 2014,
Barcelona, Spain, June 13-15, 2014},
series = {{JMLR} Workshop and Conference Proceedings},
volume = {35},
publisher = {JMLR.org},
year = {2014},
url = {http://proceedings.mlr.press/v35/},
timestamp = {Wed, 29 May 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/colt/2014.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/NeufeldGSS14,
author = {James Neufeld and
Andr{\'{a}}s Gy{\"{o}}rgy and
Dale Schuurmans and
Csaba Szepesv{\'{a}}ri},
title = {Adaptive Monte Carlo via Bandit Allocation},
journal = {CoRR},
volume = {abs/1405.3318},
year = {2014},
url = {http://arxiv.org/abs/1405.3318},
eprinttype = {arXiv},
eprint = {1405.3318},
timestamp = {Tue, 19 May 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/NeufeldGSS14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/LattimoreCS14,
author = {Tor Lattimore and
Koby Crammer and
Csaba Szepesv{\'{a}}ri},
title = {Optimal Resource Allocation with Semi-Bandit Feedback},
journal = {CoRR},
volume = {abs/1406.3840},
year = {2014},
url = {http://arxiv.org/abs/1406.3840},
eprinttype = {arXiv},
eprint = {1406.3840},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/LattimoreCS14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/Abbasi-YadkoriS14,
author = {Yasin Abbasi{-}Yadkori and
Csaba Szepesv{\'{a}}ri},
title = {Bayesian Optimal Control of Smoothly Parameterized Systems: The Lazy
Posterior Sampling Algorithm},
journal = {CoRR},
volume = {abs/1406.3926},
year = {2014},
url = {http://arxiv.org/abs/1406.3926},
eprinttype = {arXiv},
eprint = {1406.3926},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/Abbasi-YadkoriS14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/LiMS14,
author = {Lihong Li and
R{\'{e}}mi Munos and
Csaba Szepesv{\'{a}}ri},
title = {On Minimax Optimal Offline Policy Evaluation},
journal = {CoRR},
volume = {abs/1409.3653},
year = {2014},
url = {http://arxiv.org/abs/1409.3653},
eprinttype = {arXiv},
eprint = {1409.3653},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/LiMS14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/KvetonWAS14,
author = {Branislav Kveton and
Zheng Wen and
Azin Ashkan and
Csaba Szepesv{\'{a}}ri},
title = {Tight Regret Bounds for Stochastic Combinatorial Semi-Bandits},
journal = {CoRR},
volume = {abs/1410.0949},
year = {2014},
url = {http://arxiv.org/abs/1410.0949},
eprinttype = {arXiv},
eprint = {1410.0949},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/KvetonWAS14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ml/AfkanpourSB13,
author = {Arash Afkanpour and
Csaba Szepesv{\'{a}}ri and
Michael Bowling},
title = {Alignment based kernel learning with a continuous set of base kernels},
journal = {Mach. Learn.},
volume = {91},
number = {3},
pages = {305--324},
year = {2013},
url = {https://doi.org/10.1007/s10994-013-5361-8},
doi = {10.1007/S10994-013-5361-8},
timestamp = {Mon, 02 Mar 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/ml/AfkanpourSB13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tcs/AntosBPS13,
author = {Andr{\'{a}}s Antos and
G{\'{a}}bor Bart{\'{o}}k and
D{\'{a}}vid P{\'{a}}l and
Csaba Szepesv{\'{a}}ri},
title = {Toward a classification of finite partial-monitoring games},
journal = {Theor. Comput. Sci.},
volume = {473},
pages = {77--99},
year = {2013},
url = {https://doi.org/10.1016/j.tcs.2012.10.008},
doi = {10.1016/J.TCS.2012.10.008},
timestamp = {Wed, 17 Feb 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/tcs/AntosBPS13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/AfkanpourGSB13,
author = {Arash Afkanpour and
Andr{\'{a}}s Gy{\"{o}}rgy and
Csaba Szepesv{\'{a}}ri and
Michael Bowling},
title = {A Randomized Mirror Descent Algorithm for Large Scale Multiple Kernel
Learning},
booktitle = {Proceedings of the 30th International Conference on Machine Learning,
{ICML} 2013, Atlanta, GA, USA, 16-21 June 2013},
series = {{JMLR} Workshop and Conference Proceedings},
volume = {28},
pages = {374--382},
publisher = {JMLR.org},
year = {2013},
url = {http://proceedings.mlr.press/v28/afkanpour13.html},
timestamp = {Tue, 19 May 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/AfkanpourGSB13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/YuCSS13,
author = {Yaoliang Yu and
Hao Cheng and
Dale Schuurmans and
Csaba Szepesv{\'{a}}ri},
title = {Characterizing the Representer Theorem},
booktitle = {Proceedings of the 30th International Conference on Machine Learning,
{ICML} 2013, Atlanta, GA, USA, 16-21 June 2013},
series = {{JMLR} Workshop and Conference Proceedings},
volume = {28},
pages = {570--578},
publisher = {JMLR.org},
year = {2013},
url = {http://proceedings.mlr.press/v28/yu13.html},
timestamp = {Tue, 03 Nov 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icml/YuCSS13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/PiresSG13,
author = {Bernardo {\'{A}}vila Pires and
Csaba Szepesv{\'{a}}ri and
Mohammad Ghavamzadeh},
title = {Cost-sensitive Multiclass Classification Risk Bounds},
booktitle = {Proceedings of the 30th International Conference on Machine Learning,
{ICML} 2013, Atlanta, GA, USA, 16-21 June 2013},
series = {{JMLR} Workshop and Conference Proceedings},
volume = {28},
pages = {1391--1399},
publisher = {JMLR.org},
year = {2013},
url = {http://proceedings.mlr.press/v28/avilapires13.html},
timestamp = {Wed, 29 May 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/PiresSG13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/JoulaniGS13,
author = {Pooria Joulani and
Andr{\'{a}}s Gy{\"{o}}rgy and
Csaba Szepesv{\'{a}}ri},
title = {Online Learning under Delayed Feedback},
booktitle = {Proceedings of the 30th International Conference on Machine Learning,
{ICML} 2013, Atlanta, GA, USA, 16-21 June 2013},
series = {{JMLR} Workshop and Conference Proceedings},
volume = {28},
pages = {1453--1461},
publisher = {JMLR.org},
year = {2013},
url = {http://proceedings.mlr.press/v28/joulani13.html},
timestamp = {Tue, 19 May 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/JoulaniGS13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/ZolghadrBGGS13,
author = {Navid Zolghadr and
G{\'{a}}bor Bart{\'{o}}k and
Russell Greiner and
Andr{\'{a}}s Gy{\"{o}}rgy and
Csaba Szepesv{\'{a}}ri},
editor = {Christopher J. C. Burges and
L{\'{e}}on Bottou and
Zoubin Ghahramani and
Kilian Q. Weinberger},
title = {Online Learning with Costly Features and Labels},
booktitle = {Advances in Neural Information Processing Systems 26: 27th Annual
Conference on Neural Information Processing Systems 2013. Proceedings
of a meeting held December 5-8, 2013, Lake Tahoe, Nevada, United States},
pages = {1241--1249},
year = {2013},
url = {https://proceedings.neurips.cc/paper/2013/hash/291597a100aadd814d197af4f4bab3a7-Abstract.html},
timestamp = {Mon, 16 May 2022 15:41:51 +0200},
biburl = {https://dblp.org/rec/conf/nips/ZolghadrBGGS13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/Abbasi-YadkoriBKSS13,
author = {Yasin Abbasi{-}Yadkori and
Peter L. Bartlett and
Varun Kanade and
Yevgeny Seldin and
Csaba Szepesv{\'{a}}ri},
editor = {Christopher J. C. Burges and
L{\'{e}}on Bottou and
Zoubin Ghahramani and
Kilian Q. Weinberger},
title = {Online Learning in Markov Decision Processes with Adversarially Chosen
Transition Probability Distributions},
booktitle = {Advances in Neural Information Processing Systems 26: 27th Annual
Conference on Neural Information Processing Systems 2013. Proceedings
of a meeting held December 5-8, 2013, Lake Tahoe, Nevada, United States},
pages = {2508--2516},
year = {2013},
url = {https://proceedings.neurips.cc/paper/2013/hash/4f284803bd0966cc24fa8683a34afc6e-Abstract.html},
timestamp = {Thu, 21 Jan 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/Abbasi-YadkoriBKSS13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1303-3055,
author = {Yasin Abbasi{-}Yadkori and
Peter L. Bartlett and
Csaba Szepesv{\'{a}}ri},
title = {Online Learning in Markov Decision Processes with Adversarially Chosen
Transition Probability Distributions},
journal = {CoRR},
volume = {abs/1303.3055},
year = {2013},
url = {http://arxiv.org/abs/1303.3055},
eprinttype = {arXiv},
eprint = {1303.3055},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1303-3055.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/JoulaniGS13,
author = {Pooria Joulani and
Andr{\'{a}}s Gy{\"{o}}rgy and
Csaba Szepesv{\'{a}}ri},
title = {Online Learning under Delayed Feedback},
journal = {CoRR},
volume = {abs/1306.0686},
year = {2013},
url = {http://arxiv.org/abs/1306.0686},
eprinttype = {arXiv},
eprint = {1306.0686},
timestamp = {Tue, 19 May 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/JoulaniGS13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/cacm/GellyKSSSST12,
author = {Sylvain Gelly and
Levente Kocsis and
Marc Schoenauer and
Mich{\`{e}}le Sebag and
David Silver and
Csaba Szepesv{\'{a}}ri and
Olivier Teytaud},
title = {The grand challenge of computer Go: Monte Carlo tree search and extensions},
journal = {Commun. {ACM}},
volume = {55},
number = {3},
pages = {106--113},
year = {2012},
url = {https://doi.org/10.1145/2093548.2093574},
doi = {10.1145/2093548.2093574},
timestamp = {Mon, 26 Oct 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/cacm/GellyKSSSST12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/YaoS12,
author = {Hengshuai Yao and
Csaba Szepesv{\'{a}}ri},
editor = {J{\"{o}}rg Hoffmann and
Bart Selman},
title = {Approximate Policy Iteration with Linear Action Models},
booktitle = {Proceedings of the Twenty-Sixth {AAAI} Conference on Artificial Intelligence,
July 22-26, 2012, Toronto, Ontario, Canada},
pages = {1212--1218},
publisher = {{AAAI} Press},
year = {2012},
url = {https://doi.org/10.1609/aaai.v26i1.8319},
doi = {10.1609/AAAI.V26I1.8319},
timestamp = {Sat, 21 Oct 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/aaai/YaoS12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/alt/BartokS12,
author = {G{\'{a}}bor Bart{\'{o}}k and
Csaba Szepesv{\'{a}}ri},
editor = {Nader H. Bshouty and
Gilles Stoltz and
Nicolas Vayatis and
Thomas Zeugmann},
title = {Partial Monitoring with Side Information},
booktitle = {Algorithmic Learning Theory - 23rd International Conference, {ALT}
2012, Lyon, France, October 29-31, 2012. Proceedings},
series = {Lecture Notes in Computer Science},
volume = {7568},
pages = {305--319},
publisher = {Springer},
year = {2012},
url = {https://doi.org/10.1007/978-3-642-34106-9\_25},
doi = {10.1007/978-3-642-34106-9\_25},
timestamp = {Tue, 14 May 2019 10:00:51 +0200},
biburl = {https://dblp.org/rec/conf/alt/BartokS12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ewrl/DeisenrothSP12,
author = {Marc Peter Deisenroth and
Csaba Szepesv{\'{a}}ri and
Jan Peters},
editor = {Marc Peter Deisenroth and
Csaba Szepesv{\'{a}}ri and
Jan Peters},
title = {Preface},
booktitle = {Proceedings of the Tenth European Workshop on Reinforcement Learning,
{EWRL} 2012, Edinburgh, Scotland, UK, June, 2012},
series = {{JMLR} Proceedings},
volume = {24},
publisher = {JMLR.org},
year = {2012},
url = {http://proceedings.mlr.press/v24/deisenroth12a/deisenroth12a.pdf},
timestamp = {Wed, 29 May 2019 08:41:44 +0200},
biburl = {https://dblp.org/rec/conf/ewrl/DeisenrothSP12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ewrl/SeldinSAA12,
author = {Yevgeny Seldin and
Csaba Szepesv{\'{a}}ri and
Peter Auer and
Yasin Abbasi{-}Yadkori},
editor = {Marc Peter Deisenroth and
Csaba Szepesv{\'{a}}ri and
Jan Peters},
title = {Evaluation and Analysis of the Performance of the {EXP3} Algorithm
in Stochastic Environments},
booktitle = {Proceedings of the Tenth European Workshop on Reinforcement Learning,
{EWRL} 2012, Edinburgh, Scotland, UK, June, 2012},
series = {{JMLR} Proceedings},
volume = {24},
pages = {103--116},
publisher = {JMLR.org},
year = {2012},
url = {http://proceedings.mlr.press/v24/seldin12a.html},
timestamp = {Wed, 29 May 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/ewrl/SeldinSAA12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/BartokZS12,
author = {G{\'{a}}bor Bart{\'{o}}k and
Navid Zolghadr and
Csaba Szepesv{\'{a}}ri},
title = {An adaptive algorithm for finite stochastic partial monitoring},
booktitle = {Proceedings of the 29th International Conference on Machine Learning,
{ICML} 2012, Edinburgh, Scotland, UK, June 26 - July 1, 2012},
publisher = {icml.cc / Omnipress},
year = {2012},
url = {http://icml.cc/2012/papers/846.pdf},
timestamp = {Wed, 03 Apr 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/BartokZS12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/PiresS12,
author = {Bernardo {\'{A}}vila Pires and
Csaba Szepesv{\'{a}}ri},
title = {Statistical linear estimation with penalized estimators: an application
to reinforcement learning},
booktitle = {Proceedings of the 29th International Conference on Machine Learning,
{ICML} 2012, Edinburgh, Scotland, UK, June 26 - July 1, 2012},
publisher = {icml.cc / Omnipress},
year = {2012},
url = {http://icml.cc/2012/papers/759.pdf},
timestamp = {Wed, 03 Apr 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/PiresS12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/YuS12,
author = {Yaoliang Yu and
Csaba Szepesv{\'{a}}ri},
title = {Analysis of Kernel Mean Matching under Covariate Shift},
booktitle = {Proceedings of the 29th International Conference on Machine Learning,
{ICML} 2012, Edinburgh, Scotland, UK, June 26 - July 1, 2012},
publisher = {icml.cc / Omnipress},
year = {2012},
url = {http://icml.cc/2012/papers/330.pdf},
timestamp = {Wed, 03 Apr 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/YuS12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/KirosS12,
author = {Ryan Kiros and
Csaba Szepesv{\'{a}}ri},
editor = {Peter L. Bartlett and
Fernando C. N. Pereira and
Christopher J. C. Burges and
L{\'{e}}on Bottou and
Kilian Q. Weinberger},
title = {Deep Representations and Codes for Image Auto-Annotation},
booktitle = {Advances in Neural Information Processing Systems 25: 26th Annual
Conference on Neural Information Processing Systems 2012. Proceedings
of a meeting held December 3-6, 2012, Lake Tahoe, Nevada, United States},
pages = {917--925},
year = {2012},
url = {https://proceedings.neurips.cc/paper/2012/hash/3c7781a36bcd6cf08c11a970fbe0e2a6-Abstract.html},
timestamp = {Mon, 16 May 2022 15:41:51 +0200},
biburl = {https://dblp.org/rec/conf/nips/KirosS12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:journals/jmlr/Abbasi-YadkoriPS12,
author = {Yasin Abbasi{-}Yadkori and
D{\'{a}}vid P{\'{a}}l and
Csaba Szepesv{\'{a}}ri},
editor = {Neil D. Lawrence and
Mark A. Girolami},
title = {Online-to-Confidence-Set Conversions and Application to Sparse Stochastic
Bandits},
booktitle = {Proceedings of the Fifteenth International Conference on Artificial
Intelligence and Statistics, {AISTATS} 2012, La Palma, Canary Islands,
Spain, April 21-23, 2012},
series = {{JMLR} Proceedings},
volume = {22},
pages = {1--9},
publisher = {JMLR.org},
year = {2012},
url = {http://proceedings.mlr.press/v22/abbasi-yadkori12.html},
timestamp = {Wed, 29 May 2019 08:41:44 +0200},
biburl = {https://dblp.org/rec/journals/jmlr/Abbasi-YadkoriPS12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:journals/jmlr/NeuGS12,
author = {Gergely Neu and
Andr{\'{a}}s Gy{\"{o}}rgy and
Csaba Szepesv{\'{a}}ri},
editor = {Neil D. Lawrence and
Mark A. Girolami},
title = {The adversarial stochastic shortest path problem with unknown transition
probabilities},
booktitle = {Proceedings of the Fifteenth International Conference on Artificial
Intelligence and Statistics, {AISTATS} 2012, La Palma, Canary Islands,
Spain, April 21-23, 2012},
series = {{JMLR} Proceedings},
volume = {22},
pages = {805--813},
publisher = {JMLR.org},
year = {2012},
url = {http://proceedings.mlr.press/v22/neu12.html},
timestamp = {Tue, 19 May 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/jmlr/NeuGS12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@proceedings{DBLP:conf/ewrl/2012,
editor = {Marc Peter Deisenroth and
Csaba Szepesv{\'{a}}ri and
Jan Peters},
title = {Proceedings of the Tenth European Workshop on Reinforcement Learning,
{EWRL} 2012, Edinburgh, Scotland, UK, June, 2012},
series = {{JMLR} Proceedings},
volume = {24},
publisher = {JMLR.org},
year = {2012},
url = {http://proceedings.mlr.press/v24/},
timestamp = {Wed, 29 May 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/ewrl/2012.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1202-3717,
author = {Mahdi Milani Fard and
Joelle Pineau and
Csaba Szepesv{\'{a}}ri},
title = {PAC-Bayesian Policy Evaluation for Reinforcement Learning},
journal = {CoRR},
volume = {abs/1202.3717},
year = {2012},
url = {http://arxiv.org/abs/1202.3717},
eprinttype = {arXiv},
eprint = {1202.3717},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1202-3717.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1205-0288,
author = {Arash Afkanpour and
Andr{\'{a}}s Gy{\"{o}}rgy and
Csaba Szepesv{\'{a}}ri and
Michael H. Bowling},
title = {A Randomized Strategy for Learning to Combine Many Features},
journal = {CoRR},
volume = {abs/1205.0288},
year = {2012},
url = {http://arxiv.org/abs/1205.0288},
eprinttype = {arXiv},
eprint = {1205.0288},
timestamp = {Tue, 19 May 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1205-0288.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1206-3233,
author = {Alejandro Isaza and
Csaba Szepesv{\'{a}}ri and
Vadim Bulitko and
Russell Greiner},
title = {Speeding Up Planning in Markov Decision Processes via Automatically
Constructed Abstractions},
journal = {CoRR},
volume = {abs/1206.3233},
year = {2012},
url = {http://arxiv.org/abs/1206.3233},
eprinttype = {arXiv},
eprint = {1206.3233},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1206-3233.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1206-3285,
author = {Richard S. Sutton and
Csaba Szepesv{\'{a}}ri and
Alborz Geramifard and
Michael Bowling},
title = {Dyna-Style Planning with Linear Function Approximation and Prioritized
Sweeping},
journal = {CoRR},
volume = {abs/1206.3285},
year = {2012},
url = {http://arxiv.org/abs/1206.3285},
eprinttype = {arXiv},
eprint = {1206.3285},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1206-3285.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1206-4650,
author = {Yaoliang Yu and
Csaba Szepesv{\'{a}}ri},
title = {Analysis of Kernel Mean Matching under Covariate Shift},
journal = {CoRR},
volume = {abs/1206.4650},
year = {2012},
url = {http://arxiv.org/abs/1206.4650},
eprinttype = {arXiv},
eprint = {1206.4650},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1206-4650.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1206-5264,
author = {Gergely Neu and
Csaba Szepesv{\'{a}}ri},
title = {Apprenticeship Learning using Inverse Reinforcement Learning and Gradient
Methods},
journal = {CoRR},
volume = {abs/1206.5264},
year = {2012},
url = {http://arxiv.org/abs/1206.5264},
eprinttype = {arXiv},
eprint = {1206.5264},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1206-5264.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/jmlr/BubeckMSS11,
author = {S{\'{e}}bastien Bubeck and
R{\'{e}}mi Munos and
Gilles Stoltz and
Csaba Szepesv{\'{a}}ri},
title = {\emph{X}-Armed Bandits},
journal = {J. Mach. Learn. Res.},
volume = {12},
pages = {1655--1695},
year = {2011},
url = {https://dl.acm.org/doi/10.5555/1953048.2021053},
doi = {10.5555/1953048.2021053},
timestamp = {Thu, 02 Jun 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/jmlr/BubeckMSS11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ml/FarahmandS11,
author = {Amir Massoud Farahmand and
Csaba Szepesv{\'{a}}ri},
title = {Model selection in reinforcement learning},
journal = {Mach. Learn.},
volume = {85},
number = {3},
pages = {299--332},
year = {2011},
url = {https://doi.org/10.1007/s10994-011-5254-7},
doi = {10.1007/S10994-011-5254-7},
timestamp = {Mon, 02 Mar 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/ml/FarahmandS11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/alt/KivinenSUZ11,
author = {Jyrki Kivinen and
Csaba Szepesv{\'{a}}ri and
Esko Ukkonen and
Thomas Zeugmann},
editor = {Jyrki Kivinen and
Csaba Szepesv{\'{a}}ri and
Esko Ukkonen and
Thomas Zeugmann},
title = {Editors' Introduction},
booktitle = {Algorithmic Learning Theory - 22nd International Conference, {ALT}
2011, Espoo, Finland, October 5-7, 2011. Proceedings},
series = {Lecture Notes in Computer Science},
volume = {6925},
pages = {1--13},
publisher = {Springer},
year = {2011},
url = {https://doi.org/10.1007/978-3-642-24412-4\_1},
doi = {10.1007/978-3-642-24412-4\_1},
timestamp = {Tue, 14 May 2019 10:00:51 +0200},
biburl = {https://dblp.org/rec/conf/alt/KivinenSUZ11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ewrl/Szepesvari11,
author = {Csaba Szepesv{\'{a}}ri},
editor = {Scott Sanner and
Marcus Hutter},
title = {Invited Talk: Towards Robust Reinforcement Learning Algorithms},
booktitle = {Recent Advances in Reinforcement Learning - 9th European Workshop,
{EWRL} 2011, Athens, Greece, September 9-11, 2011, Revised Selected
Papers},
series = {Lecture Notes in Computer Science},
volume = {7188},
pages = {4},
publisher = {Springer},
year = {2011},
url = {https://doi.org/10.1007/978-3-642-29946-9\_4},
doi = {10.1007/978-3-642-29946-9\_4},
timestamp = {Tue, 14 May 2019 10:00:48 +0200},
biburl = {https://dblp.org/rec/conf/ewrl/Szepesvari11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/infocom/AroraSZ11,
author = {Pallavi Arora and
Csaba Szepesv{\'{a}}ri and
Rong Zheng},
title = {Sequential learning for optimal monitoring of multi-channel wireless
networks},
booktitle = {{INFOCOM} 2011. 30th {IEEE} International Conference on Computer Communications,
Joint Conference of the {IEEE} Computer and Communications Societies,
10-15 April 2011, Shanghai, China},
pages = {1152--1160},
publisher = {{IEEE}},
year = {2011},
url = {https://doi.org/10.1109/INFCOM.2011.5934892},
doi = {10.1109/INFCOM.2011.5934892},
timestamp = {Wed, 16 Oct 2019 14:14:51 +0200},
biburl = {https://dblp.org/rec/conf/infocom/AroraSZ11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/Abbasi-YadkoriPS11,
author = {Yasin Abbasi{-}Yadkori and
D{\'{a}}vid P{\'{a}}l and
Csaba Szepesv{\'{a}}ri},
editor = {John Shawe{-}Taylor and
Richard S. Zemel and
Peter L. Bartlett and
Fernando C. N. Pereira and
Kilian Q. Weinberger},
title = {Improved Algorithms for Linear Stochastic Bandits},
booktitle = {Advances in Neural Information Processing Systems 24: 25th Annual
Conference on Neural Information Processing Systems 2011. Proceedings
of a meeting held 12-14 December 2011, Granada, Spain},
pages = {2312--2320},
year = {2011},
url = {https://proceedings.neurips.cc/paper/2011/hash/e1d5be1c7f2f456670de3d53c7b54f4a-Abstract.html},
timestamp = {Mon, 16 May 2022 15:41:51 +0200},
biburl = {https://dblp.org/rec/conf/nips/Abbasi-YadkoriPS11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/uai/FardPS11,
author = {Mahdi Milani Fard and
Joelle Pineau and
Csaba Szepesv{\'{a}}ri},
editor = {F{\'{a}}bio Gagliardi Cozman and
Avi Pfeffer},
title = {PAC-Bayesian Policy Evaluation for Reinforcement Learning},
booktitle = {{UAI} 2011, Proceedings of the Twenty-Seventh Conference on Uncertainty
in Artificial Intelligence, Barcelona, Spain, July 14-17, 2011},
pages = {195--202},
publisher = {{AUAI} Press},
year = {2011},
url = {https://dslpitt.org/uai/displayArticleDetails.jsp?mmnu=1\&\#38;smnu=2\&\#38;article\_id=2218\&\#38;proceeding\_id=27},
timestamp = {Wed, 03 Feb 2021 11:09:03 +0100},
biburl = {https://dblp.org/rec/conf/uai/FardPS11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:journals/jmlr/Abbasi-YadkoriS11,
author = {Yasin Abbasi{-}Yadkori and
Csaba Szepesv{\'{a}}ri},
editor = {Sham M. Kakade and
Ulrike von Luxburg},
title = {Regret Bounds for the Adaptive Control of Linear Quadratic Systems},
booktitle = {{COLT} 2011 - The 24th Annual Conference on Learning Theory, June
9-11, 2011, Budapest, Hungary},
series = {{JMLR} Proceedings},
volume = {19},
pages = {1--26},
publisher = {JMLR.org},
year = {2011},
url = {http://proceedings.mlr.press/v19/abbasi-yadkori11a/abbasi-yadkori11a.pdf},
timestamp = {Wed, 29 May 2019 08:41:47 +0200},
biburl = {https://dblp.org/rec/journals/jmlr/Abbasi-YadkoriS11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:journals/jmlr/BartokPS11,
author = {G{\'{a}}bor Bart{\'{o}}k and
D{\'{a}}vid P{\'{a}}l and
Csaba Szepesv{\'{a}}ri},
editor = {Sham M. Kakade and
Ulrike von Luxburg},
title = {Minimax Regret of Finite Partial-Monitoring Games in Stochastic Environments},
booktitle = {{COLT} 2011 - The 24th Annual Conference on Learning Theory, June
9-11, 2011, Budapest, Hungary},
series = {{JMLR} Proceedings},
volume = {19},
pages = {133--154},
publisher = {JMLR.org},
year = {2011},
url = {http://proceedings.mlr.press/v19/bartok11a/bartok11a.pdf},
timestamp = {Wed, 29 May 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/jmlr/BartokPS11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:journals/jmlr/SzitaS11,
author = {Istv{\'{a}}n Szita and
Csaba Szepesv{\'{a}}ri},
editor = {Sham M. Kakade and
Ulrike von Luxburg},
title = {Agnostic {KWIK} learning and efficient approximate reinforcement learning},
booktitle = {{COLT} 2011 - The 24th Annual Conference on Learning Theory, June
9-11, 2011, Budapest, Hungary},
series = {{JMLR} Proceedings},
volume = {19},
pages = {739--772},
publisher = {JMLR.org},
year = {2011},
url = {http://proceedings.mlr.press/v19/szita11a/szita11a.pdf},
timestamp = {Wed, 29 May 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/jmlr/SzitaS11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@proceedings{DBLP:conf/alt/2011,
editor = {Jyrki Kivinen and
Csaba Szepesv{\'{a}}ri and
Esko Ukkonen and
Thomas Zeugmann},
title = {Algorithmic Learning Theory - 22nd International Conference, {ALT}
2011, Espoo, Finland, October 5-7, 2011. Proceedings},
series = {Lecture Notes in Computer Science},
volume = {6925},
publisher = {Springer},
year = {2011},
url = {https://doi.org/10.1007/978-3-642-24412-4},
doi = {10.1007/978-3-642-24412-4},
isbn = {978-3-642-24411-7},
timestamp = {Tue, 14 May 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/alt/2011.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1102-2041,
author = {Andr{\'{a}}s Antos and
G{\'{a}}bor Bart{\'{o}}k and
D{\'{a}}vid P{\'{a}}l and
Csaba Szepesv{\'{a}}ri},
title = {Toward a Classification of Finite Partial-Monitoring Games},
journal = {CoRR},
volume = {abs/1102.2041},
year = {2011},
url = {http://arxiv.org/abs/1102.2041},
eprinttype = {arXiv},
eprint = {1102.2041},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1102-2041.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1102-2670,
author = {Yasin Abbasi{-}Yadkori and
D{\'{a}}vid P{\'{a}}l and
Csaba Szepesv{\'{a}}ri},
title = {Online Least Squares Estimation with Self-Normalized Processes: An
Application to Bandit Problems},
journal = {CoRR},
volume = {abs/1102.2670},
year = {2011},
url = {http://arxiv.org/abs/1102.2670},
eprinttype = {arXiv},
eprint = {1102.2670},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1102-2670.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1108-4961,
author = {Andr{\'{a}}s Antos and
G{\'{a}}bor Bart{\'{o}}k and
Csaba Szepesv{\'{a}}ri},
title = {Non-trivial two-armed partial-monitoring games are bandits},
journal = {CoRR},
volume = {abs/1108.4961},
year = {2011},
url = {http://arxiv.org/abs/1108.4961},
eprinttype = {arXiv},
eprint = {1108.4961},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1108-4961.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1112-4607,
author = {Arash Afkanpour and
Csaba Szepesv{\'{a}}ri and
Michael H. Bowling},
title = {Alignment Based Kernel Learning with a Continuous Set of Base Kernels},
journal = {CoRR},
volume = {abs/1112.4607},
year = {2011},
url = {http://arxiv.org/abs/1112.4607},
eprinttype = {arXiv},
eprint = {1112.4607},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1112-4607.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@book{DBLP:series/synthesis/2010Szepesvari,
author = {Csaba Szepesv{\'{a}}ri},
title = {Algorithms for Reinforcement Learning},
series = {Synthesis Lectures on Artificial Intelligence and Machine Learning},
publisher = {Morgan {\&} Claypool Publishers},
year = {2010},
url = {https://doi.org/10.2200/S00268ED1V01Y201005AIM009},
doi = {10.2200/S00268ED1V01Y201005AIM009},
isbn = {978-3-031-00423-0},
timestamp = {Tue, 17 Oct 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/series/synthesis/2010Szepesvari.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/iandc/BartokSZ10,
author = {G{\'{a}}bor Bart{\'{o}}k and
Csaba Szepesv{\'{a}}ri and
Sandra Zilles},
title = {Models of active learning in group-structured state spaces},
journal = {Inf. Comput.},
volume = {208},
number = {4},
pages = {364--384},
year = {2010},
url = {https://doi.org/10.1016/j.ic.2009.09.001},
doi = {10.1016/J.IC.2009.09.001},
timestamp = {Fri, 12 Feb 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/iandc/BartokSZ10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tcs/AntosGS10,
author = {Andr{\'{a}}s Antos and
Varun Grover and
Csaba Szepesv{\'{a}}ri},
title = {Active learning in heteroscedastic noise},
journal = {Theor. Comput. Sci.},
volume = {411},
number = {29-30},
pages = {2712--2728},
year = {2010},
url = {https://doi.org/10.1016/j.tcs.2010.04.007},
doi = {10.1016/J.TCS.2010.04.007},
timestamp = {Wed, 17 Feb 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/tcs/AntosGS10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/alt/BartokPS10,
author = {G{\'{a}}bor Bart{\'{o}}k and
D{\'{a}}vid P{\'{a}}l and
Csaba Szepesv{\'{a}}ri},
editor = {Marcus Hutter and
Frank Stephan and
Vladimir Vovk and
Thomas Zeugmann},
title = {Toward a Classification of Finite Partial-Monitoring Games},
booktitle = {Algorithmic Learning Theory, 21st International Conference, {ALT}
2010, Canberra, Australia, October 6-8, 2010. Proceedings},
series = {Lecture Notes in Computer Science},
volume = {6331},
pages = {224--238},
publisher = {Springer},
year = {2010},
url = {https://doi.org/10.1007/978-3-642-16108-7\_20},
doi = {10.1007/978-3-642-16108-7\_20},
timestamp = {Tue, 14 May 2019 10:00:51 +0200},
biburl = {https://dblp.org/rec/conf/alt/BartokPS10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/colt/NeuGS10,
author = {Gergely Neu and
Andr{\'{a}}s Gy{\"{o}}rgy and
Csaba Szepesv{\'{a}}ri},
editor = {Adam Tauman Kalai and
Mehryar Mohri},
title = {The Online Loop-free Stochastic Shortest-Path Problem},
booktitle = {{COLT} 2010 - The 23rd Conference on Learning Theory, Haifa, Israel,
June 27-29, 2010},
pages = {231--243},
publisher = {Omnipress},
year = {2010},
url = {http://colt2010.haifa.il.ibm.com/papers/COLT2010proceedings.pdf\#page=239},
timestamp = {Tue, 25 Jan 2022 13:23:33 +0100},
biburl = {https://dblp.org/rec/conf/colt/NeuGS10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/MaeiSBS10,
author = {Hamid Reza Maei and
Csaba Szepesv{\'{a}}ri and
Shalabh Bhatnagar and
Richard S. Sutton},
editor = {Johannes F{\"{u}}rnkranz and
Thorsten Joachims},
title = {Toward Off-Policy Learning Control with Function Approximation},
booktitle = {Proceedings of the 27th International Conference on Machine Learning
(ICML-10), June 21-24, 2010, Haifa, Israel},
pages = {719--726},
publisher = {Omnipress},
year = {2010},
url = {https://icml.cc/Conferences/2010/papers/627.pdf},
timestamp = {Wed, 03 Apr 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/MaeiSBS10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/LiPSG10,
author = {Liuyang Li and
Barnab{\'{a}}s P{\'{o}}czos and
Csaba Szepesv{\'{a}}ri and
Russell Greiner},
editor = {Johannes F{\"{u}}rnkranz and
Thorsten Joachims},
title = {Budgeted Distribution Learning of Belief Net Parameters},
booktitle = {Proceedings of the 27th International Conference on Machine Learning
(ICML-10), June 21-24, 2010, Haifa, Israel},
pages = {879--886},
publisher = {Omnipress},
year = {2010},
url = {https://icml.cc/Conferences/2010/papers/406.pdf},
timestamp = {Wed, 03 Apr 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/LiPSG10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/SzitaS10,
author = {Istvan Szita and
Csaba Szepesv{\'{a}}ri},
editor = {Johannes F{\"{u}}rnkranz and
Thorsten Joachims},
title = {Model-based reinforcement learning with nearly tight exploration complexity
bounds},
booktitle = {Proceedings of the 27th International Conference on Machine Learning
(ICML-10), June 21-24, 2010, Haifa, Israel},
pages = {1031--1038},
publisher = {Omnipress},
year = {2010},
url = {https://icml.cc/Conferences/2010/papers/546.pdf},
timestamp = {Wed, 03 Apr 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/SzitaS10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iros/Abbasi-YadkoriMS10,
author = {Yasin Abbasi{-}Yadkori and
Joseph Modayil and
Csaba Szepesv{\'{a}}ri},
title = {Extending rapidly-exploring random trees for asymptotically optimal
anytime motion planning},
booktitle = {2010 {IEEE/RSJ} International Conference on Intelligent Robots and
Systems, October 18-22, 2010, Taipei, Taiwan},
pages = {127--132},
publisher = {{IEEE}},
year = {2010},
url = {https://doi.org/10.1109/IROS.2010.5650614},
doi = {10.1109/IROS.2010.5650614},
timestamp = {Wed, 16 Oct 2019 14:14:51 +0200},
biburl = {https://dblp.org/rec/conf/iros/Abbasi-YadkoriMS10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/FarahmandMS10,
author = {Amir Massoud Farahmand and
R{\'{e}}mi Munos and
Csaba Szepesv{\'{a}}ri},
editor = {John D. Lafferty and
Christopher K. I. Williams and
John Shawe{-}Taylor and
Richard S. Zemel and
Aron Culotta},
title = {Error Propagation for Approximate Policy and Value Iteration},
booktitle = {Advances in Neural Information Processing Systems 23: 24th Annual
Conference on Neural Information Processing Systems 2010. Proceedings
of a meeting held 6-9 December 2010, Vancouver, British Columbia,
Canada},
pages = {568--576},
publisher = {Curran Associates, Inc.},
year = {2010},
url = {https://proceedings.neurips.cc/paper/2010/hash/65cc2c8205a05d7379fa3a6386f710e1-Abstract.html},
timestamp = {Mon, 16 May 2022 15:41:51 +0200},
biburl = {https://dblp.org/rec/conf/nips/FarahmandMS10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/FilippiCGS10,
author = {Sarah Filippi and
Olivier Capp{\'{e}} and
Aur{\'{e}}lien Garivier and
Csaba Szepesv{\'{a}}ri},
editor = {John D. Lafferty and
Christopher K. I. Williams and
John Shawe{-}Taylor and
Richard S. Zemel and
Aron Culotta},
title = {Parametric Bandits: The Generalized Linear Case},
booktitle = {Advances in Neural Information Processing Systems 23: 24th Annual
Conference on Neural Information Processing Systems 2010. Proceedings
of a meeting held 6-9 December 2010, Vancouver, British Columbia,
Canada},
pages = {586--594},
publisher = {Curran Associates, Inc.},
year = {2010},
url = {https://proceedings.neurips.cc/paper/2010/hash/c2626d850c80ea07e7511bbae4c76f4b-Abstract.html},
timestamp = {Thu, 21 Jan 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/FilippiCGS10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/NeuGSA10,
author = {Gergely Neu and
Andr{\'{a}}s Gy{\"{o}}rgy and
Csaba Szepesv{\'{a}}ri and
Andr{\'{a}}s Antos},
editor = {John D. Lafferty and
Christopher K. I. Williams and
John Shawe{-}Taylor and
Richard S. Zemel and
Aron Culotta},
title = {Online Markov Decision Processes under Bandit Feedback},
booktitle = {Advances in Neural Information Processing Systems 23: 24th Annual
Conference on Neural Information Processing Systems 2010. Proceedings
of a meeting held 6-9 December 2010, Vancouver, British Columbia,
Canada},
pages = {1804--1812},
publisher = {Curran Associates, Inc.},
year = {2010},
url = {https://proceedings.neurips.cc/paper/2010/hash/7bb060764a818184ebb1cc0d43d382aa-Abstract.html},
timestamp = {Thu, 21 Jan 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/NeuGSA10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/PalPS10,
author = {D{\'{a}}vid P{\'{a}}l and
Barnab{\'{a}}s P{\'{o}}czos and
Csaba Szepesv{\'{a}}ri},
editor = {John D. Lafferty and
Christopher K. I. Williams and
John Shawe{-}Taylor and
Richard S. Zemel and
Aron Culotta},
title = {Estimation of Renyi Entropy and Mutual Information Based on Generalized
Nearest-Neighbor Graphs},
booktitle = {Advances in Neural Information Processing Systems 23: 24th Annual
Conference on Neural Information Processing Systems 2010. Proceedings
of a meeting held 6-9 December 2010, Vancouver, British Columbia,
Canada},
pages = {1849--1857},
publisher = {Curran Associates, Inc.},
year = {2010},
url = {https://proceedings.neurips.cc/paper/2010/hash/577ef1154f3240ad5b9b413aa7346a1e-Abstract.html},
timestamp = {Thu, 21 Jan 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/PalPS10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:journals/jmlr/PoczosKS10,
author = {Barnab{\'{a}}s P{\'{o}}czos and
Sergey Kirshner and
Csaba Szepesv{\'{a}}ri},
editor = {Yee Whye Teh and
D. Mike Titterington},
title = {{REGO:} Rank-based Estimation of Renyi Information using Euclidean
Graph Optimization},
booktitle = {Proceedings of the Thirteenth International Conference on Artificial
Intelligence and Statistics, {AISTATS} 2010, Chia Laguna Resort, Sardinia,
Italy, May 13-15, 2010},
series = {{JMLR} Proceedings},
volume = {9},
pages = {605--612},
publisher = {JMLR.org},
year = {2010},
url = {http://proceedings.mlr.press/v9/poczos10a.html},
timestamp = {Wed, 29 May 2019 08:41:44 +0200},
biburl = {https://dblp.org/rec/journals/jmlr/PoczosKS10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:journals/jmlr/TormaGS10,
author = {P{\'{e}}ter Torma and
Andr{\'{a}}s Gy{\"{o}}rgy and
Csaba Szepesv{\'{a}}ri},
editor = {Yee Whye Teh and
D. Mike Titterington},
title = {A Markov-Chain Monte Carlo Approach to Simultaneous Localization and
Mapping},
booktitle = {Proceedings of the Thirteenth International Conference on Artificial
Intelligence and Statistics, {AISTATS} 2010, Chia Laguna Resort, Sardinia,
Italy, May 13-15, 2010},
series = {{JMLR} Proceedings},
volume = {9},
pages = {852--859},
publisher = {JMLR.org},
year = {2010},
url = {http://proceedings.mlr.press/v9/torma10a.html},
timestamp = {Tue, 19 May 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/jmlr/TormaGS10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1001-4475,
author = {S{\'{e}}bastien Bubeck and
R{\'{e}}mi Munos and
Gilles Stoltz and
Csaba Szepesv{\'{a}}ri},
title = {X-Armed Bandits},
journal = {CoRR},
volume = {abs/1001.4475},
year = {2010},
url = {http://arxiv.org/abs/1001.4475},
eprinttype = {arXiv},
eprint = {1001.4475},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1001-4475.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1003-1954,
author = {D{\'{a}}vid P{\'{a}}l and
Barnab{\'{a}}s P{\'{o}}czos and
Csaba Szepesv{\'{a}}ri},
title = {Estimation of R{\'{e}}nyi Entropy and Mutual Information Based
on Generalized Nearest-Neighbor Graphs},
journal = {CoRR},
volume = {abs/1003.1954},
year = {2010},
url = {http://arxiv.org/abs/1003.1954},
eprinttype = {arXiv},
eprint = {1003.1954},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1003-1954.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ml/NeuS09,
author = {Gergely Neu and
Csaba Szepesv{\'{a}}ri},
title = {Training parsers by inverse reinforcement learning},
journal = {Mach. Learn.},
volume = {77},
number = {2-3},
pages = {303--337},
year = {2009},
url = {https://doi.org/10.1007/s10994-009-5110-1},
doi = {10.1007/S10994-009-5110-1},
timestamp = {Mon, 26 Oct 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/ml/NeuS09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tcs/AudibertMS09,
author = {Jean{-}Yves Audibert and
R{\'{e}}mi Munos and
Csaba Szepesv{\'{a}}ri},
title = {Exploration-exploitation tradeoff using variance estimates in multi-armed
bandits},
journal = {Theor. Comput. Sci.},
volume = {410},
number = {19},
pages = {1876--1902},
year = {2009},
url = {https://doi.org/10.1016/j.tcs.2009.01.016},
doi = {10.1016/J.TCS.2009.01.016},
timestamp = {Wed, 17 Feb 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/tcs/AudibertMS09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/amcc/FarahmandGSM09,
author = {Amir Massoud Farahmand and
Mohammad Ghavamzadeh and
Csaba Szepesv{\'{a}}ri and
Shie Mannor},
title = {Regularized Fitted Q-Iteration for planning in continuous-space Markovian
decision problems},
booktitle = {American Control Conference, {ACC} 2009. St. Louis, Missouri, USA,
June 10-12, 2009},
pages = {725--730},
publisher = {{IEEE}},
year = {2009},
url = {https://doi.org/10.1109/ACC.2009.5160611},
doi = {10.1109/ACC.2009.5160611},
timestamp = {Fri, 03 Dec 2021 13:02:58 +0100},
biburl = {https://dblp.org/rec/conf/amcc/FarahmandGSM09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/cdc/YaoBS09,
author = {Hengshuai Yao and
Shalabh Bhatnagar and
Csaba Szepesv{\'{a}}ri},
title = {{LMS-2:} Towards an algorithm that is as cheap as {LMS} and almost
as efficient as {RLS}},
booktitle = {Proceedings of the 48th {IEEE} Conference on Decision and Control,
{CDC} 2009, combined withe the 28th Chinese Control Conference, December
16-18, 2009, Shanghai, China},
pages = {1181--1188},
publisher = {{IEEE}},
year = {2009},
url = {https://doi.org/10.1109/CDC.2009.5400370},
doi = {10.1109/CDC.2009.5400370},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/cdc/YaoBS09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/AudibertALMRS09,
author = {Jean{-}Yves Audibert and
Peter Auer and
Alessandro Lazaric and
R{\'{e}}mi Munos and
Daniil Ryabko and
Csaba Szepesv{\'{a}}ri},
editor = {Andrea Pohoreckyj Danyluk and
L{\'{e}}on Bottou and
Michael L. Littman},
title = {Workshop summary: On-line learning with limited feedback},
booktitle = {Proceedings of the 26th Annual International Conference on Machine
Learning, {ICML} 2009, Montreal, Quebec, Canada, June 14-18, 2009},
series = {{ACM} International Conference Proceeding Series},
volume = {382},
pages = {8},
publisher = {{ACM}},
year = {2009},
url = {https://doi.org/10.1145/1553374.1553547},
doi = {10.1145/1553374.1553547},
timestamp = {Tue, 06 Nov 2018 16:58:29 +0100},
biburl = {https://dblp.org/rec/conf/icml/AudibertALMRS09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/FarhangfarGS09,
author = {Alireza Farhangfar and
Russell Greiner and
Csaba Szepesv{\'{a}}ri},
editor = {Andrea Pohoreckyj Danyluk and
L{\'{e}}on Bottou and
Michael L. Littman},
title = {Learning to segment from a few well-selected training images},
booktitle = {Proceedings of the 26th Annual International Conference on Machine
Learning, {ICML} 2009, Montreal, Quebec, Canada, June 14-18, 2009},
series = {{ACM} International Conference Proceeding Series},
volume = {382},
pages = {305--312},
publisher = {{ACM}},
year = {2009},
url = {https://doi.org/10.1145/1553374.1553413},
doi = {10.1145/1553374.1553413},
timestamp = {Tue, 06 Nov 2018 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icml/FarhangfarGS09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/PoczosASGS09,
author = {Barnab{\'{a}}s P{\'{o}}czos and
Yasin Abbasi{-}Yadkori and
Csaba Szepesv{\'{a}}ri and
Russell Greiner and
Nathan R. Sturtevant},
editor = {Andrea Pohoreckyj Danyluk and
L{\'{e}}on Bottou and
Michael L. Littman},
title = {Learning when to stop thinking and do something!},
booktitle = {Proceedings of the 26th Annual International Conference on Machine
Learning, {ICML} 2009, Montreal, Quebec, Canada, June 14-18, 2009},
series = {{ACM} International Conference Proceeding Series},
volume = {382},
pages = {825--832},
publisher = {{ACM}},
year = {2009},
url = {https://doi.org/10.1145/1553374.1553480},
doi = {10.1145/1553374.1553480},
timestamp = {Tue, 06 Nov 2018 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icml/PoczosASGS09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/SuttonMPBSSW09,
author = {Richard S. Sutton and
Hamid Reza Maei and
Doina Precup and
Shalabh Bhatnagar and
David Silver and
Csaba Szepesv{\'{a}}ri and
Eric Wiewiora},
editor = {Andrea Pohoreckyj Danyluk and
L{\'{e}}on Bottou and
Michael L. Littman},
title = {Fast gradient-descent methods for temporal-difference learning with
linear function approximation},
booktitle = {Proceedings of the 26th Annual International Conference on Machine
Learning, {ICML} 2009, Montreal, Quebec, Canada, June 14-18, 2009},
series = {{ACM} International Conference Proceeding Series},
volume = {382},
pages = {993--1000},
publisher = {{ACM}},
year = {2009},
url = {https://doi.org/10.1145/1553374.1553501},
doi = {10.1145/1553374.1553501},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/SuttonMPBSSW09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icra/FarahmandSJS09,
author = {Amir Massoud Farahmand and
Azad Shademan and
Martin J{\"{a}}gersand and
Csaba Szepesv{\'{a}}ri},
title = {Model-based and model-free reinforcement learning for visual servoing},
booktitle = {2009 {IEEE} International Conference on Robotics and Automation, {ICRA}
2009, Kobe, Japan, May 12-17, 2009},
pages = {2917--2924},
publisher = {{IEEE}},
year = {2009},
url = {https://doi.org/10.1109/ROBOT.2009.5152834},
doi = {10.1109/ROBOT.2009.5152834},
timestamp = {Mon, 22 May 2017 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icra/FarahmandSJS09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/MaeiSBPSS09,
author = {Hamid Reza Maei and
Csaba Szepesv{\'{a}}ri and
Shalabh Bhatnagar and
Doina Precup and
David Silver and
Richard S. Sutton},
editor = {Yoshua Bengio and
Dale Schuurmans and
John D. Lafferty and
Christopher K. I. Williams and
Aron Culotta},
title = {Convergent Temporal-Difference Learning with Arbitrary Smooth Function
Approximation},
booktitle = {Advances in Neural Information Processing Systems 22: 23rd Annual
Conference on Neural Information Processing Systems 2009. Proceedings
of a meeting held 7-10 December 2009, Vancouver, British Columbia,
Canada},
pages = {1204--1212},
publisher = {Curran Associates, Inc.},
year = {2009},
url = {https://proceedings.neurips.cc/paper/2009/hash/3a15c7d0bbe60300a39f76f8a5ba6896-Abstract.html},
timestamp = {Mon, 16 May 2022 15:41:51 +0200},
biburl = {https://dblp.org/rec/conf/nips/MaeiSBPSS09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/YaoSBDS09,
author = {Hengshuai Yao and
Richard S. Sutton and
Shalabh Bhatnagar and
Diao Dongcui and
Csaba Szepesv{\'{a}}ri},
editor = {Yoshua Bengio and
Dale Schuurmans and
John D. Lafferty and
Christopher K. I. Williams and
Aron Culotta},
title = {Multi-Step Dyna Planning for Policy Evaluation and Control},
booktitle = {Advances in Neural Information Processing Systems 22: 23rd Annual
Conference on Neural Information Processing Systems 2009. Proceedings
of a meeting held 7-10 December 2009, Vancouver, British Columbia,
Canada},
pages = {2187--2195},
publisher = {Curran Associates, Inc.},
year = {2009},
url = {https://proceedings.neurips.cc/paper/2009/hash/c52f1bd66cc19d05628bd8bf27af3ad6-Abstract.html},
timestamp = {Thu, 21 Jan 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/YaoSBDS09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/YuLSS09,
author = {Yaoliang Yu and
Yuxi Li and
Dale Schuurmans and
Csaba Szepesv{\'{a}}ri},
editor = {Yoshua Bengio and
Dale Schuurmans and
John D. Lafferty and
Christopher K. I. Williams and
Aron Culotta},
title = {A General Projection Property for Distribution Families},
booktitle = {Advances in Neural Information Processing Systems 22: 23rd Annual
Conference on Neural Information Processing Systems 2009. Proceedings
of a meeting held 7-10 December 2009, Vancouver, British Columbia,
Canada},
pages = {2232--2240},
publisher = {Curran Associates, Inc.},
year = {2009},
url = {https://proceedings.neurips.cc/paper/2009/hash/a684eceee76fc522773286a895bc8436-Abstract.html},
timestamp = {Thu, 21 Jan 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/YuLSS09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:journals/jmlr/LiSS09,
author = {Yuxi Li and
Csaba Szepesv{\'{a}}ri and
Dale Schuurmans},
editor = {David A. Van Dyk and
Max Welling},
title = {Learning Exercise Policies for American Options},
booktitle = {Proceedings of the Twelfth International Conference on Artificial
Intelligence and Statistics, {AISTATS} 2009, Clearwater Beach, Florida,
USA, April 16-18, 2009},
series = {{JMLR} Proceedings},
volume = {5},
pages = {352--359},
publisher = {JMLR.org},
year = {2009},
url = {http://proceedings.mlr.press/v5/li09d.html},
timestamp = {Wed, 29 May 2019 08:41:44 +0200},
biburl = {https://dblp.org/rec/journals/jmlr/LiSS09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/jmlr/MunosS08,
author = {R{\'{e}}mi Munos and
Csaba Szepesv{\'{a}}ri},
title = {Finite-Time Bounds for Fitted Value Iteration},
journal = {J. Mach. Learn. Res.},
volume = {9},
pages = {815--857},
year = {2008},
url = {https://dl.acm.org/doi/10.5555/1390681.1390708},
doi = {10.5555/1390681.1390708},
timestamp = {Thu, 02 Jun 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/jmlr/MunosS08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ml/AntosSM08,
author = {Andr{\'{a}}s Antos and
Csaba Szepesv{\'{a}}ri and
R{\'{e}}mi Munos},
title = {Learning near-optimal policies with Bellman-residual minimization
based fitted policy iteration and a single sample path},
journal = {Mach. Learn.},
volume = {71},
number = {1},
pages = {89--129},
year = {2008},
url = {https://doi.org/10.1007/s10994-007-5038-2},
doi = {10.1007/S10994-007-5038-2},
timestamp = {Mon, 02 Mar 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/ml/AntosSM08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/alt/AntosGS08,
author = {Andr{\'{a}}s Antos and
Varun Grover and
Csaba Szepesv{\'{a}}ri},
editor = {Yoav Freund and
L{\'{a}}szl{\'{o}} Gy{\"{o}}rfi and
Gy{\"{o}}rgy Tur{\'{a}}n and
Thomas Zeugmann},
title = {Active Learning in Multi-armed Bandits},
booktitle = {Algorithmic Learning Theory, 19th International Conference, {ALT}
2008, Budapest, Hungary, October 13-16, 2008. Proceedings},
series = {Lecture Notes in Computer Science},
volume = {5254},
pages = {287--302},
publisher = {Springer},
year = {2008},
url = {https://doi.org/10.1007/978-3-540-87987-9\_25},
doi = {10.1007/978-3-540-87987-9\_25},
timestamp = {Tue, 14 May 2019 10:00:51 +0200},
biburl = {https://dblp.org/rec/conf/alt/AntosGS08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/alt/BartokSZ08,
author = {G{\'{a}}bor Bart{\'{o}}k and
Csaba Szepesv{\'{a}}ri and
Sandra Zilles},
editor = {Yoav Freund and
L{\'{a}}szl{\'{o}} Gy{\"{o}}rfi and
Gy{\"{o}}rgy Tur{\'{a}}n and
Thomas Zeugmann},
title = {Active Learning of Group-Structured Environments},
booktitle = {Algorithmic Learning Theory, 19th International Conference, {ALT}
2008, Budapest, Hungary, October 13-16, 2008. Proceedings},
series = {Lecture Notes in Computer Science},
volume = {5254},
pages = {329--343},
publisher = {Springer},
year = {2008},
url = {https://doi.org/10.1007/978-3-540-87987-9\_28},
doi = {10.1007/978-3-540-87987-9\_28},
timestamp = {Fri, 26 May 2017 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/alt/BartokSZ08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ewrl/FarahmandGSM08,
author = {Amir Massoud Farahmand and
Mohammad Ghavamzadeh and
Csaba Szepesv{\'{a}}ri and
Shie Mannor},
editor = {Sertan Girgin and
Manuel Loth and
R{\'{e}}mi Munos and
Philippe Preux and
Daniil Ryabko},
title = {Regularized Fitted Q-Iteration: Application to Planning},
booktitle = {Recent Advances in Reinforcement Learning, 8th European Workshop,
{EWRL} 2008, Villeneuve d'Ascq, France, June 30 - July 3, 2008, Revised
and Selected Papers},
series = {Lecture Notes in Computer Science},
volume = {5323},
pages = {55--68},
publisher = {Springer},
year = {2008},
url = {https://doi.org/10.1007/978-3-540-89722-4\_5},
doi = {10.1007/978-3-540-89722-4\_5},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/ewrl/FarahmandGSM08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/MnihSA08,
author = {Volodymyr Mnih and
Csaba Szepesv{\'{a}}ri and
Jean{-}Yves Audibert},
editor = {William W. Cohen and
Andrew McCallum and
Sam T. Roweis},
title = {Empirical Bernstein stopping},
booktitle = {Machine Learning, Proceedings of the Twenty-Fifth International Conference
{(ICML} 2008), Helsinki, Finland, June 5-9, 2008},
series = {{ACM} International Conference Proceeding Series},
volume = {307},
pages = {672--679},
publisher = {{ACM}},
year = {2008},
url = {https://doi.org/10.1145/1390156.1390241},
doi = {10.1145/1390156.1390241},
timestamp = {Tue, 06 Nov 2018 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icml/MnihSA08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/BubeckMSS08,
author = {S{\'{e}}bastien Bubeck and
R{\'{e}}mi Munos and
Gilles Stoltz and
Csaba Szepesv{\'{a}}ri},
editor = {Daphne Koller and
Dale Schuurmans and
Yoshua Bengio and
L{\'{e}}on Bottou},
title = {Online Optimization in X-Armed Bandits},
booktitle = {Advances in Neural Information Processing Systems 21, Proceedings
of the Twenty-Second Annual Conference on Neural Information Processing
Systems, Vancouver, British Columbia, Canada, December 8-11, 2008},
pages = {201--208},
publisher = {Curran Associates, Inc.},
year = {2008},
url = {https://proceedings.neurips.cc/paper/2008/hash/f387624df552cea2f369918c5e1e12bc-Abstract.html},
timestamp = {Mon, 16 May 2022 15:41:51 +0200},
biburl = {https://dblp.org/rec/conf/nips/BubeckMSS08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/FarahmandGSM08,
author = {Amir Massoud Farahmand and
Mohammad Ghavamzadeh and
Csaba Szepesv{\'{a}}ri and
Shie Mannor},
editor = {Daphne Koller and
Dale Schuurmans and
Yoshua Bengio and
L{\'{e}}on Bottou},
title = {Regularized Policy Iteration},
booktitle = {Advances in Neural Information Processing Systems 21, Proceedings
of the Twenty-Second Annual Conference on Neural Information Processing
Systems, Vancouver, British Columbia, Canada, December 8-11, 2008},
pages = {441--448},
publisher = {Curran Associates, Inc.},
year = {2008},
url = {https://proceedings.neurips.cc/paper/2008/hash/aeb3135b436aa55373822c010763dd54-Abstract.html},
timestamp = {Thu, 21 Jan 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/FarahmandGSM08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/SuttonSM08,
author = {Richard S. Sutton and
Csaba Szepesv{\'{a}}ri and
Hamid Reza Maei},
editor = {Daphne Koller and
Dale Schuurmans and
Yoshua Bengio and
L{\'{e}}on Bottou},
title = {A Convergent O(n) Temporal-difference Algorithm for Off-policy Learning
with Linear Function Approximation},
booktitle = {Advances in Neural Information Processing Systems 21, Proceedings
of the Twenty-Second Annual Conference on Neural Information Processing
Systems, Vancouver, British Columbia, Canada, December 8-11, 2008},
pages = {1609--1616},
publisher = {Curran Associates, Inc.},
year = {2008},
url = {https://proceedings.neurips.cc/paper/2008/hash/e0c641195b27425bb056ac56f8953d24-Abstract.html},
timestamp = {Thu, 21 Jan 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/SuttonSM08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/uai/IsazaSBG08,
author = {Alejandro Isaza and
Csaba Szepesv{\'{a}}ri and
Vadim Bulitko and
Russell Greiner},
editor = {David A. McAllester and
Petri Myllym{\"{a}}ki},
title = {Speeding Up Planning in Markov Decision Processes via Automatically
Constructed Abstraction},
booktitle = {{UAI} 2008, Proceedings of the 24th Conference in Uncertainty in Artificial
Intelligence, Helsinki, Finland, July 9-12, 2008},
pages = {306--314},
publisher = {{AUAI} Press},
year = {2008},
url = {https://dslpitt.org/uai/displayArticleDetails.jsp?mmnu=1\&\#38;smnu=2\&\#38;article\_id=1955\&\#38;proceeding\_id=24},
timestamp = {Wed, 03 Feb 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/uai/IsazaSBG08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/uai/SuttonSGB08,
author = {Richard S. Sutton and
Csaba Szepesv{\'{a}}ri and
Alborz Geramifard and
Michael H. Bowling},
editor = {David A. McAllester and
Petri Myllym{\"{a}}ki},
title = {Dyna-Style Planning with Linear Function Approximation and Prioritized
Sweeping},
booktitle = {{UAI} 2008, Proceedings of the 24th Conference in Uncertainty in Artificial
Intelligence, Helsinki, Finland, July 9-12, 2008},
pages = {528--536},
publisher = {{AUAI} Press},
year = {2008},
url = {https://dslpitt.org/uai/displayArticleDetails.jsp?mmnu=1\&\#38;smnu=2\&\#38;article\_id=1971\&\#38;proceeding\_id=24},
timestamp = {Wed, 03 Feb 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/uai/SuttonSGB08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/alt/AudibertMS07,
author = {Jean{-}Yves Audibert and
R{\'{e}}mi Munos and
Csaba Szepesv{\'{a}}ri},
editor = {Marcus Hutter and
Rocco A. Servedio and
Eiji Takimoto},
title = {Tuning Bandit Algorithms in Stochastic Environments},
booktitle = {Algorithmic Learning Theory, 18th International Conference, {ALT}
2007, Sendai, Japan, October 1-4, 2007, Proceedings},
series = {Lecture Notes in Computer Science},
volume = {4754},
pages = {150--165},
publisher = {Springer},
year = {2007},
url = {https://doi.org/10.1007/978-3-540-75225-7\_15},
doi = {10.1007/978-3-540-75225-7\_15},
timestamp = {Tue, 14 May 2019 10:00:51 +0200},
biburl = {https://dblp.org/rec/conf/alt/AudibertMS07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/colt/AuerOS07,
author = {Peter Auer and
Ronald Ortner and
Csaba Szepesv{\'{a}}ri},
editor = {Nader H. Bshouty and
Claudio Gentile},
title = {Improved Rates for the Stochastic Continuum-Armed Bandit Problem},
booktitle = {Learning Theory, 20th Annual Conference on Learning Theory, {COLT}
2007, San Diego, CA, USA, June 13-15, 2007, Proceedings},
series = {Lecture Notes in Computer Science},
volume = {4539},
pages = {454--468},
publisher = {Springer},
year = {2007},
url = {https://doi.org/10.1007/978-3-540-72927-3\_33},
doi = {10.1007/978-3-540-72927-3\_33},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/colt/AuerOS07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/FarahmandSA07,
author = {Amir Massoud Farahmand and
Csaba Szepesv{\'{a}}ri and
Jean{-}Yves Audibert},
editor = {Zoubin Ghahramani},
title = {Manifold-adaptive dimension estimation},
booktitle = {Machine Learning, Proceedings of the Twenty-Fourth International Conference
{(ICML} 2007), Corvallis, Oregon, USA, June 20-24, 2007},
series = {{ACM} International Conference Proceeding Series},
volume = {227},
pages = {265--272},
publisher = {{ACM}},
year = {2007},
url = {https://doi.org/10.1145/1273496.1273530},
doi = {10.1145/1273496.1273530},
timestamp = {Tue, 06 Nov 2018 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icml/FarahmandSA07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ijcai/GyorgyKSS07,
author = {Andr{\'{a}}s Gy{\"{o}}rgy and
Levente Kocsis and
Ivett Szab{\'{o}} and
Csaba Szepesv{\'{a}}ri},
editor = {Manuela M. Veloso},
title = {Continuous Time Associative Bandit Problems},
booktitle = {{IJCAI} 2007, Proceedings of the 20th International Joint Conference
on Artificial Intelligence, Hyderabad, India, January 6-12, 2007},
pages = {830--835},
year = {2007},
url = {http://ijcai.org/Proceedings/07/Papers/133.pdf},
timestamp = {Tue, 19 May 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/ijcai/GyorgyKSS07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ijcai/BiroSS07,
author = {Istv{\'{a}}n B{\'{\i}}r{\'{o}} and
Zolt{\'{a}}n Szamonek and
Csaba Szepesv{\'{a}}ri},
editor = {Manuela M. Veloso},
title = {Sequence Prediction Exploiting Similary Information},
booktitle = {{IJCAI} 2007, Proceedings of the 20th International Joint Conference
on Artificial Intelligence, Hyderabad, India, January 6-12, 2007},
pages = {1576--1581},
year = {2007},
url = {http://ijcai.org/Proceedings/07/Papers/254.pdf},
timestamp = {Tue, 20 Aug 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/ijcai/BiroSS07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/AntosMS07,
author = {Andr{\'{a}}s Antos and
R{\'{e}}mi Munos and
Csaba Szepesv{\'{a}}ri},
editor = {John C. Platt and
Daphne Koller and
Yoram Singer and
Sam T. Roweis},
title = {Fitted Q-iteration in continuous action-space MDPs},
booktitle = {Advances in Neural Information Processing Systems 20, Proceedings
of the Twenty-First Annual Conference on Neural Information Processing
Systems, Vancouver, British Columbia, Canada, December 3-6, 2007},
pages = {9--16},
publisher = {Curran Associates, Inc.},
year = {2007},
url = {https://proceedings.neurips.cc/paper/2007/hash/da0d1111d2dc5d489242e60ebcbaf988-Abstract.html},
timestamp = {Mon, 16 May 2022 15:41:51 +0200},
biburl = {https://dblp.org/rec/conf/nips/AntosMS07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/uai/NeuS07,
author = {Gergely Neu and
Csaba Szepesv{\'{a}}ri},
editor = {Ronald Parr and
Linda C. van der Gaag},
title = {Apprenticeship Learning using Inverse Reinforcement Learning and Gradient
Methods},
booktitle = {{UAI} 2007, Proceedings of the Twenty-Third Conference on Uncertainty
in Artificial Intelligence, Vancouver, BC, Canada, July 19-22, 2007},
pages = {295--302},
publisher = {{AUAI} Press},
year = {2007},
url = {https://dslpitt.org/uai/displayArticleDetails.jsp?mmnu=1\&\#38;smnu=2\&\#38;article\_id=1702\&\#38;proceeding\_id=23},
timestamp = {Wed, 03 Feb 2021 11:09:18 +0100},
biburl = {https://dblp.org/rec/conf/uai/NeuS07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/jmm2/TormaS06,
author = {P{\'{e}}ter Torma and
Csaba Szepesv{\'{a}}ri},
title = {Local Importance Sampling: {A} Novel Technique to Enhance Particle
Filtering},
journal = {J. Multim.},
volume = {1},
number = {1},
pages = {32--43},
year = {2006},
url = {https://doi.org/10.4304/jmm.1.1.32-43},
doi = {10.4304/JMM.1.1.32-43},
timestamp = {Fri, 18 Sep 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/jmm2/TormaS06.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ml/KocsisS06,
author = {Levente Kocsis and
Csaba Szepesv{\'{a}}ri},
title = {Universal parameter optimisation in games based on {SPSA}},
journal = {Mach. Learn.},
volume = {63},
number = {3},
pages = {249--286},
year = {2006},
url = {https://doi.org/10.1007/s10994-006-6888-8},
doi = {10.1007/S10994-006-6888-8},
timestamp = {Mon, 02 Mar 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/ml/KocsisS06.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/acg/KocsisSW06,
author = {Levente Kocsis and
Csaba Szepesv{\'{a}}ri and
Mark H. M. Winands},
editor = {H. Jaap van den Herik and
Shun{-}chin Hsu and
Tsan{-}sheng Hsu and
H. H. L. M. Donkers},
title = {{RSPSA:} Enhanced Parameter Optimization in Games},
booktitle = {Advances in Computer Games, 11th International Conference, {ACG} 2005,
Taipei, Taiwan, September 6-9, 2005. Revised Papers},
series = {Lecture Notes in Computer Science},
volume = {4250},
pages = {39--56},
publisher = {Springer},
year = {2006},
url = {https://doi.org/10.1007/11922155\_4},
doi = {10.1007/11922155\_4},
timestamp = {Tue, 14 May 2019 10:00:53 +0200},
biburl = {https://dblp.org/rec/conf/acg/KocsisSW06.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/colt/AntosSM06,
author = {Andr{\'{a}}s Antos and
Csaba Szepesv{\'{a}}ri and
R{\'{e}}mi Munos},
editor = {G{\'{a}}bor Lugosi and
Hans Ulrich Simon},
title = {Learning Near-Optimal Policies with Bellman-Residual Minimization
Based Fitted Policy Iteration and a Single Sample Path},
booktitle = {Learning Theory, 19th Annual Conference on Learning Theory, {COLT}
2006, Pittsburgh, PA, USA, June 22-25, 2006, Proceedings},
series = {Lecture Notes in Computer Science},
volume = {4005},
pages = {574--588},
publisher = {Springer},
year = {2006},
url = {https://doi.org/10.1007/11776420\_42},
doi = {10.1007/11776420\_42},
timestamp = {Fri, 08 Sep 2023 21:18:17 +0200},
biburl = {https://dblp.org/rec/conf/colt/AntosSM06.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ecml/KocsisS06,
author = {Levente Kocsis and
Csaba Szepesv{\'{a}}ri},
editor = {Johannes F{\"{u}}rnkranz and
Tobias Scheffer and
Myra Spiliopoulou},
title = {Bandit Based Monte-Carlo Planning},
booktitle = {Machine Learning: {ECML} 2006, 17th European Conference on Machine
Learning, Berlin, Germany, September 18-22, 2006, Proceedings},
series = {Lecture Notes in Computer Science},
volume = {4212},
pages = {282--293},
publisher = {Springer},
year = {2006},
url = {https://doi.org/10.1007/11871842\_29},
doi = {10.1007/11871842\_29},
timestamp = {Tue, 14 May 2019 10:00:54 +0200},
biburl = {https://dblp.org/rec/conf/ecml/KocsisS06.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icdm/SzamonekS05,
author = {Zolt{\'{a}}n Szamonek and
Csaba Szepesv{\'{a}}ri},
title = {X-mHMM: An Efficient Algorithm for Training Mixtures of HMMs When
the Number of Mixtures Is Unknown},
booktitle = {Proceedings of the 5th {IEEE} International Conference on Data Mining
{(ICDM} 2005), 27-30 November 2005, Houston, Texas, {USA}},
pages = {434--441},
publisher = {{IEEE} Computer Society},
year = {2005},
url = {https://doi.org/10.1109/ICDM.2005.156},
doi = {10.1109/ICDM.2005.156},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icdm/SzamonekS05.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/SzepesvariM05,
author = {Csaba Szepesv{\'{a}}ri and
R{\'{e}}mi Munos},
editor = {Luc De Raedt and
Stefan Wrobel},
title = {Finite time bounds for sampling based fitted value iteration},
booktitle = {Machine Learning, Proceedings of the Twenty-Second International Conference
{(ICML} 2005), Bonn, Germany, August 7-11, 2005},
series = {{ACM} International Conference Proceeding Series},
volume = {119},
pages = {880--887},
publisher = {{ACM}},
year = {2005},
url = {https://doi.org/10.1145/1102351.1102462},
doi = {10.1145/1102351.1102462},
timestamp = {Tue, 06 Nov 2018 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icml/SzepesvariM05.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/Szepesvari04,
author = {Csaba Szepesv{\'{a}}ri},
editor = {Deborah L. McGuinness and
George Ferguson},
title = {Shortest Path Discovery Problems: {A} Framework, Algorithms and Experimental
Results},
booktitle = {Proceedings of the Nineteenth National Conference on Artificial Intelligence,
Sixteenth Conference on Innovative Applications of Artificial Intelligence,
July 25-29, 2004, San Jose, California, {USA}},
pages = {550--555},
publisher = {{AAAI} Press / The {MIT} Press},
year = {2004},
url = {http://www.aaai.org/Library/AAAI/2004/aaai04-088.php},
timestamp = {Tue, 05 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/aaai/Szepesvari04.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ecai/SzepesvariKK04,
author = {Csaba Szepesv{\'{a}}ri and
Andr{\'{a}}s Kocsor and
Korn{\'{e}}l Kov{\'{a}}cs},
editor = {Ram{\'{o}}n L{\'{o}}pez de M{\'{a}}ntaras and
Lorenza Saitta},
title = {Kernel Machine Based Feature Extraction Algorithms for Regression
Problems},
booktitle = {Proceedings of the 16th Eureopean Conference on Artificial Intelligence,
ECAI'2004, including Prestigious Applicants of Intelligent Systems,
{PAIS} 2004, Valencia, Spain, August 22-27, 2004},
pages = {1091--1092},
publisher = {{IOS} Press},
year = {2004},
timestamp = {Fri, 11 May 2018 12:42:30 +0200},
biburl = {https://dblp.org/rec/conf/ecai/SzepesvariKK04.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/eccv/TormaS04,
author = {P{\'{e}}ter Torma and
Csaba Szepesv{\'{a}}ri},
editor = {Tom{\'{a}}s Pajdla and
Jiri Matas},
title = {Enhancing Particle Filters Using Local Likelihood Sampling},
booktitle = {Computer Vision - {ECCV} 2004, 8th European Conference on Computer
Vision, Prague, Czech Republic, May 11-14, 2004. Proceedings, Part
{I}},
series = {Lecture Notes in Computer Science},
volume = {3021},
pages = {16--27},
publisher = {Springer},
year = {2004},
url = {https://doi.org/10.1007/978-3-540-24670-1\_2},
doi = {10.1007/978-3-540-24670-1\_2},
timestamp = {Tue, 14 May 2019 10:00:45 +0200},
biburl = {https://dblp.org/rec/conf/eccv/TormaS04.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ecml/KocsorKS04,
author = {Andr{\'{a}}s Kocsor and
Korn{\'{e}}l Kov{\'{a}}cs and
Csaba Szepesv{\'{a}}ri},
editor = {Jean{-}Fran{\c{c}}ois Boulicaut and
Floriana Esposito and
Fosca Giannotti and
Dino Pedreschi},
title = {Margin Maximizing Discriminant Analysis},
booktitle = {Machine Learning: {ECML} 2004, 15th European Conference on Machine
Learning, Pisa, Italy, September 20-24, 2004, Proceedings},
series = {Lecture Notes in Computer Science},
volume = {3201},
pages = {227--238},
publisher = {Springer},
year = {2004},
url = {https://doi.org/10.1007/978-3-540-30115-8\_23},
doi = {10.1007/978-3-540-30115-8\_23},
timestamp = {Tue, 14 May 2019 10:00:54 +0200},
biburl = {https://dblp.org/rec/conf/ecml/KocsorKS04.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/SzepesvariS04,
author = {Csaba Szepesv{\'{a}}ri and
William D. Smart},
editor = {Carla E. Brodley},
title = {Interpolation-based Q-learning},
booktitle = {Machine Learning, Proceedings of the Twenty-first International Conference
{(ICML} 2004), Banff, Alberta, Canada, July 4-8, 2004},
series = {{ACM} International Conference Proceeding Series},
volume = {69},
publisher = {{ACM}},
year = {2004},
url = {https://doi.org/10.1145/1015330.1015445},
doi = {10.1145/1015330.1015445},
timestamp = {Tue, 06 Nov 2018 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icml/SzepesvariS04.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aistats/TormaS03,
author = {P{\'{e}}ter Torma and
Csaba Szepesv{\'{a}}ri},
editor = {Christopher M. Bishop and
Brendan J. Frey},
title = {Sequential Importance Sampling for Visual Tracking Reconsidered},
booktitle = {Proceedings of the Ninth International Workshop on Artificial Intelligence
and Statistics, {AISTATS} 2003, Key West, Florida, USA, January 3-6,
2003},
publisher = {Society for Artificial Intelligence and Statistics},
year = {2003},
url = {http://research.microsoft.com/en-us/um/cambridge/events/aistats2003/proceedings/198.pdf},
timestamp = {Wed, 06 May 2015 20:33:21 +0200},
biburl = {https://dblp.org/rec/conf/aistats/TormaS03.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/automatica/FrenchSR02,
author = {Mark French and
Csaba Szepesv{\'{a}}ri and
Eric Rogers},
title = {{LQ} performance bounds for adaptive output feedback controllers for
functionally uncertain nonlinear systems},
journal = {Autom.},
volume = {38},
number = {4},
pages = {683--693},
year = {2002},
url = {https://doi.org/10.1016/S0005-1098(01)00218-7},
doi = {10.1016/S0005-1098(01)00218-7},
timestamp = {Thu, 20 Feb 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/automatica/FrenchSR02.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/mcss/FrenchSR02,
author = {Mark French and
Csaba Szepesv{\'{a}}ri and
Eric Rogers},
title = {An Asymptotic Scaling Analysis of {LQ} Performance for an Approximate
Adaptive Control Design},
journal = {Math. Control. Signals Syst.},
volume = {15},
number = {2},
pages = {145--176},
year = {2002},
url = {https://doi.org/10.1007/s004980200006},
doi = {10.1007/S004980200006},
timestamp = {Thu, 10 Sep 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/mcss/FrenchSR02.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/aicom/Szepesvari01,
author = {Csaba Szepesv{\'{a}}ri},
title = {Efficient approximate planning in continuous space Markovian Decision
Problems},
journal = {{AI} Commun.},
volume = {14},
number = {3},
pages = {163--176},
year = {2001},
url = {http://content.iospress.com/articles/ai-communications/aic244},
timestamp = {Fri, 15 May 2015 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/aicom/Szepesvari01.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ijns/LorinczHS01,
author = {Andr{\'{a}}s L{\"{o}}rincz and
Gy{\"{o}}rgy H{\'{e}}v{\'{\i}}zi and
Csaba Szepesv{\'{a}}ri},
title = {Ockham's Razor Modeling of the Matrisome Channels of the Basal Ganglia
Thalamocortical Loops},
journal = {Int. J. Neural Syst.},
volume = {11},
number = {2},
pages = {125--143},
year = {2001},
url = {https://doi.org/10.1142/S0129065701000412},
doi = {10.1142/S0129065701000412},
timestamp = {Wed, 14 Nov 2018 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/ijns/LorinczHS01.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/actaC/KalmarSL00,
author = {Zsolt Kalm{\'{a}}r and
Csaba Szepesv{\'{a}}ri and
Andr{\'{a}}s L{\"{o}}rincz},
title = {Modular Reinforcement Learning: {A} Case Study in a Robot Domain},
journal = {Acta Cybern.},
volume = {14},
number = {3},
pages = {507--522},
year = {2000},
url = {https://cyber.bibl.u-szeged.hu/index.php/actcybern/article/view/3546},
timestamp = {Wed, 16 Sep 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/actaC/KalmarSL00.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ml/SinghJLS00,
author = {Satinder Singh and
Tommi S. Jaakkola and
Michael L. Littman and
Csaba Szepesv{\'{a}}ri},
title = {Convergence Results for Single-Step On-Policy Reinforcement-Learning
Algorithms},
journal = {Mach. Learn.},
volume = {38},
number = {3},
pages = {287--308},
year = {2000},
url = {https://doi.org/10.1023/A:1007678930559},
doi = {10.1023/A:1007678930559},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/ml/SinghJLS00.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tac/FrenchSR00,
author = {Mark French and
Csaba Szepesv{\'{a}}ri and
Eric Rogers},
title = {Uncertainty, performance, and model dependency in approximate adaptive
nonlinear control},
journal = {{IEEE} Trans. Autom. Control.},
volume = {45},
number = {2},
pages = {353--358},
year = {2000},
url = {https://doi.org/10.1109/9.839965},
doi = {10.1109/9.839965},
timestamp = {Wed, 20 May 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/tac/FrenchSR00.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/tsd/BaloghDGSS00,
author = {Gy{\"{o}}rgy Balogh and
Ervin Dobler and
Tam{\'{a}}s Gr{\"{o}}bler and
B{\'{e}}la Smodics and
Csaba Szepesv{\'{a}}ri},
editor = {Petr Sojka and
Ivan Kopecek and
Karel Pala},
title = {FlexVoice: {A} Parametric Approach to High-Quality Speech Synthesis},
booktitle = {Text, Speech and Dialogue - Third International Workshop, {TSD} 2000,
Brno, Czech Republic, September 13-16, 2000, Proceedings},
series = {Lecture Notes in Computer Science},
volume = {1902},
pages = {189--194},
publisher = {Springer},
year = {2000},
url = {https://doi.org/10.1007/3-540-45323-7\_32},
doi = {10.1007/3-540-45323-7\_32},
timestamp = {Tue, 14 May 2019 10:00:45 +0200},
biburl = {https://dblp.org/rec/conf/tsd/BaloghDGSS00.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/nar/MurvaiVBSAP99,
author = {J{\'{a}}nos Murvai and
Kristian Vlahovicek and
Endre Barta and
Csaba Szepesv{\'{a}}ri and
Cristina Acatrinei and
S{\'{a}}ndor Pongor},
title = {The {SBASE} protein domain library, release 6.0: a collection of annotated
protein sequence segments},
journal = {Nucleic Acids Res.},
volume = {27},
number = {1},
pages = {257--259},
year = {1999},
url = {https://doi.org/10.1093/nar/27.1.257},
doi = {10.1093/NAR/27.1.257},
timestamp = {Fri, 09 Apr 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/nar/MurvaiVBSAP99.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/neco/SzepesvariL99,
author = {Csaba Szepesv{\'{a}}ri and
Michael L. Littman},
title = {A Unified Analysis of Value-Function-Based Reinforcement Learning
Algorithms},
journal = {Neural Comput.},
volume = {11},
number = {8},
pages = {2017--2060},
year = {1999},
url = {https://doi.org/10.1162/089976699300016070},
doi = {10.1162/089976699300016070},
timestamp = {Tue, 01 Sep 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/neco/SzepesvariL99.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/nn/KalmarMSL99,
author = {Zsolt Kalm{\'{a}}r and
Zsolt Marczell and
Csaba Szepesv{\'{a}}ri and
Andr{\'{a}}s L{\"{o}}rincz},
title = {Parallel and robust skeletonization built on self-organizing elements},
journal = {Neural Networks},
volume = {12},
number = {1},
pages = {163--173},
year = {1999},
url = {https://doi.org/10.1016/S0893-6080(98)00119-1},
doi = {10.1016/S0893-6080(98)00119-1},
timestamp = {Wed, 14 Nov 2018 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/nn/KalmarMSL99.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/actaC/Szepesvari98,
author = {Csaba Szepesv{\'{a}}ri},
title = {Non-Markovian Policies in Sequential Decision Problems},
journal = {Acta Cybern.},
volume = {13},
number = {3},
pages = {305--318},
year = {1998},
url = {https://cyber.bibl.u-szeged.hu/index.php/actcybern/article/view/3493},
timestamp = {Wed, 16 Sep 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/actaC/Szepesvari98.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/arobots/KalmarSL98,
author = {Zsolt Kalm{\'{a}}r and
Csaba Szepesv{\'{a}}ri and
Andr{\'{a}}s L{\"{o}}rincz},
title = {Module-Based Reinforcement Learning: Experiments with a Real Robot},
journal = {Auton. Robots},
volume = {5},
number = {3-4},
pages = {273--295},
year = {1998},
url = {https://doi.org/10.1023/A:1008858222277},
doi = {10.1023/A:1008858222277},
timestamp = {Thu, 18 May 2017 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/arobots/KalmarSL98.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/jfr/SzepesvariL98,
author = {Csaba Szepesv{\'{a}}ri and
Andr{\'{a}}s L{\"{o}}rincz},
title = {An integrated architecture for motion-control and path-planning},
journal = {J. Field Robotics},
volume = {15},
number = {1},
pages = {1--15},
year = {1998},
url = {https://doi.org/10.1002/(SICI)1097-4563(199812)15:1\&\#60;1::AID-ROB1\&\#62;3.0.CO;2-V},
doi = {10.1002/(SICI)1097-4563(199812)15:1\&\#60;1::AID-ROB1\&\#62;3.0.CO;2-V},
timestamp = {Sun, 28 May 2017 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/jfr/SzepesvariL98.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ml/KalmarSL98,
author = {Zsolt Kalm{\'{a}}r and
Csaba Szepesv{\'{a}}ri and
Andr{\'{a}}s L{\"{o}}rincz},
title = {Module-Based Reinforcement Learning: Experiments with a Real Robot},
journal = {Mach. Learn.},
volume = {31},
number = {1-3},
pages = {55--85},
year = {1998},
url = {https://doi.org/10.1023/A:1007440607681},
doi = {10.1023/A:1007440607681},
timestamp = {Mon, 02 Mar 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/ml/KalmarSL98.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/GaborKS98,
author = {Zolt{\'{a}}n G{\'{a}}bor and
Zsolt Kalm{\'{a}}r and
Csaba Szepesv{\'{a}}ri},
editor = {Jude W. Shavlik},
title = {Multi-criteria Reinforcement Learning},
booktitle = {Proceedings of the Fifteenth International Conference on Machine Learning
{(ICML} 1998), Madison, Wisconsin, USA, July 24-27, 1998},
pages = {197--205},
publisher = {Morgan Kaufmann},
year = {1998},
timestamp = {Thu, 30 Jun 2011 10:34:12 +0200},
biburl = {https://dblp.org/rec/conf/icml/GaborKS98.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/mammo/SorantinSMWS98,
author = {Erich Sorantin and
Ferdinand Schmidt and
Heinz Mayer and
Peter Winkler and
Csaba Szepesv{\'{a}}ri},
editor = {Nico Karssemeijer and
Martin Thijssen and
Jan H. C. L. Hendriks and
Leon van Erning},
title = {Automated Detection and Classification of Micro-Calcifications in
Mammograms Using Artifical Neural Nets},
booktitle = {Digital Mammography, Fourth International Workshop on Digital Mammograph,
{IWDM} 1998, Nijmegen, The Netherlands, June 1998},
series = {Computational Imaging and Vision},
volume = {13},
pages = {225--232},
publisher = {Springer},
year = {1998},
url = {https://doi.org/10.1007/978-94-011-5318-8\_37},
doi = {10.1007/978-94-011-5318-8\_37},
timestamp = {Fri, 19 Jul 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/mammo/SorantinSMWS98.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/mammo/WinklerSTSMS98,
author = {Peter Winkler and
Erich Sorantin and
Attila Tan{\'{a}}cs and
Ferdinand Schmidt and
Heinz Mayer and
Csaba Szepesv{\'{a}}ri},
editor = {Nico Karssemeijer and
Martin Thijssen and
Jan H. C. L. Hendriks and
Leon van Erning},
title = {Performance-Evaluation for Automated Detection of Microcalcifications
in Mammograms Using Three Different Film-Digitizers},
booktitle = {Digital Mammography, Fourth International Workshop on Digital Mammograph,
{IWDM} 1998, Nijmegen, The Netherlands, June 1998},
series = {Computational Imaging and Vision},
volume = {13},
pages = {485--486},
publisher = {Springer},
year = {1998},
url = {https://doi.org/10.1007/978-94-011-5318-8\_83},
doi = {10.1007/978-94-011-5318-8\_83},
timestamp = {Fri, 19 Jul 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/mammo/WinklerSTSMS98.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/nn/SzepesvariCL97,
author = {Csaba Szepesv{\'{a}}ri and
Szabolcs Cimmer and
Andr{\'{a}}s L{\"{o}}rincz},
title = {Neurocontroller using dynamic state feedback for compensatory control},
journal = {Neural Networks},
volume = {10},
number = {9},
pages = {1691--1708},
year = {1997},
url = {https://doi.org/10.1016/S0893-6080(97)00043-9},
doi = {10.1016/S0893-6080(97)00043-9},
timestamp = {Thu, 08 Jun 2017 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/nn/SzepesvariCL97.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ecml/Szepesvari97,
author = {Csaba Szepesv{\'{a}}ri},
editor = {Maarten van Someren and
Gerhard Widmer},
title = {Learning and Exploitation Do Not Conflict Under Minimax Optimality},
booktitle = {Machine Learning: ECML-97, 9th European Conference on Machine Learning,
Prague, Czech Republic, April 23-25, 1997, Proceedings},
series = {Lecture Notes in Computer Science},
volume = {1224},
pages = {242--249},
publisher = {Springer},
year = {1997},
url = {https://doi.org/10.1007/3-540-62858-4\_89},
doi = {10.1007/3-540-62858-4\_89},
timestamp = {Tue, 14 May 2019 10:00:54 +0200},
biburl = {https://dblp.org/rec/conf/ecml/Szepesvari97.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ewlr/KalmarSL97,
author = {Zsolt Kalm{\'{a}}r and
Csaba Szepesv{\'{a}}ri and
Andr{\'{a}}s L{\"{o}}rincz},
editor = {Andreas Birk and
John Demiris},
title = {Module Based Reinforcement Learning: An Application to a Real Robot},
booktitle = {Learning Robots, 6th European Workshop, EWLR-6, Brighton, England,
UK, August 1-2, 1997, Proceedings},
series = {Lecture Notes in Computer Science},
volume = {1545},
pages = {29--45},
publisher = {Springer},
year = {1997},
url = {https://doi.org/10.1007/3-540-49240-2\_3},
doi = {10.1007/3-540-49240-2\_3},
timestamp = {Tue, 14 May 2019 10:00:49 +0200},
biburl = {https://dblp.org/rec/conf/ewlr/KalmarSL97.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/Szepesvari97,
author = {Csaba Szepesv{\'{a}}ri},
editor = {Michael I. Jordan and
Michael J. Kearns and
Sara A. Solla},
title = {The Asymptotic Convergence-Rate of Q-learning},
booktitle = {Advances in Neural Information Processing Systems 10, {[NIPS} Conference,
Denver, Colorado, USA, 1997]},
pages = {1064--1070},
publisher = {The {MIT} Press},
year = {1997},
url = {http://papers.nips.cc/paper/1383-the-asymptotic-convergence-rate-of-q-learning},
timestamp = {Mon, 16 May 2022 15:41:51 +0200},
biburl = {https://dblp.org/rec/conf/nips/Szepesvari97.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ijns/FominRSL96,
author = {Tibor Fomin and
Tam{\'{a}}s Rozgonyi and
Csaba Szepesv{\'{a}}ri and
Andr{\'{a}}s L{\"{o}}rincz},
title = {Self-Organizing Multi-Resolution Grid for Motion Planning and Control},
journal = {Int. J. Neural Syst.},
volume = {7},
number = {6},
pages = {757},
year = {1996},
url = {http://ejournals.wspc.com.sg/ijns/07/0706/fomin.html},
timestamp = {Fri, 16 Jul 2004 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/ijns/FominRSL96.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ijon/SzepesvariL96,
author = {Csaba Szepesv{\'{a}}ri and
Andr{\'{a}}s L{\"{o}}rincz},
title = {Approximate geometry representations and sensory fusion},
journal = {Neurocomputing},
volume = {12},
number = {2-3},
pages = {267--287},
year = {1996},
url = {https://doi.org/10.1016/0925-2312(95)00116-6},
doi = {10.1016/0925-2312(95)00116-6},
timestamp = {Tue, 06 Jun 2017 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/ijon/SzepesvariL96.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icann/SzepesvariL96,
author = {Csaba Szepesv{\'{a}}ri and
Andr{\'{a}}s L{\"{o}}rincz},
editor = {Christoph von der Malsburg and
Werner von Seelen and
Jan C. Vorbr{\"{u}}ggen and
Bernhard Sendhoff},
title = {Inverse Dynamics Controllers for Robust Control: Consequences for
Neurocontrollers},
booktitle = {Artificial Neural Networks - {ICANN} 96, 1996 International Conference,
Bochum, Germany, July 16-19, 1996, Proceedings},
series = {Lecture Notes in Computer Science},
volume = {1112},
pages = {791--796},
publisher = {Springer},
year = {1996},
url = {https://doi.org/10.1007/3-540-61510-5\_133},
doi = {10.1007/3-540-61510-5\_133},
timestamp = {Tue, 14 May 2019 10:00:49 +0200},
biburl = {https://dblp.org/rec/conf/icann/SzepesvariL96.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/LittmanS96,
author = {Michael L. Littman and
Csaba Szepesv{\'{a}}ri},
editor = {Lorenza Saitta},
title = {A Generalized Reinforcement-Learning Model: Convergence and Applications},
booktitle = {Machine Learning, Proceedings of the Thirteenth International Conference
{(ICML} '96), Bari, Italy, July 3-6, 1996},
pages = {310--318},
publisher = {Morgan Kaufmann},
year = {1996},
timestamp = {Fri, 23 Dec 2011 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icml/LittmanS96.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/neco/SzepesvariBL94,
author = {Csaba Szepesv{\'{a}}ri and
L{\'{a}}szl{\'{o}} Bal{\'{a}}zs and
Andr{\'{a}}s L{\"{o}}rincz},
title = {Topology Learning Solved by Extended Objects: {A} Neural Network Model},
journal = {Neural Comput.},
volume = {6},
number = {3},
pages = {441--458},
year = {1994},
url = {https://doi.org/10.1162/neco.1994.6.3.441},
doi = {10.1162/NECO.1994.6.3.441},
timestamp = {Mon, 28 Aug 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/neco/SzepesvariBL94.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/adb/SzepesvariL93,
author = {Csaba Szepesv{\'{a}}ri and
Andr{\'{a}}s L{\"{o}}rincz},
title = {Behavior of an Adaptive Self-organizing Autonomous Agent Working with
Cues and Competing Concepts},
journal = {Adapt. Behav.},
volume = {2},
number = {2},
pages = {131--160},
year = {1993},
url = {https://doi.org/10.1177/105971239300200202},
doi = {10.1177/105971239300200202},
timestamp = {Tue, 25 Aug 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/adb/SzepesvariL93.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
a service of 
manage site settings
To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.
last updated on 2024-04-25 05:49 CEST by the dblp team
all metadata released as open data under CC0 1.0 license
see also: Terms of Use | Privacy Policy | Imprint
dblp was originally created in 1993 at:
since 2018, dblp has been operated and maintained by:
the dblp computer science bibliography is funded and supported by:
