26. ICML 2009:
Montreal, Quebec, Canada
Hal Daumé III
: Unsupervised search-based structured prediction.
, Rohit Khandekar
: Gradient descent with sparsification: an iterative algorithm for sparse recovery with restricted isometry property.
(paper withdrawn). ...
, Filip Zelezný
: Block-wise construction of acyclic relational features with monotone irreducibility and relevancy properties.
: ABC-boost: adaptive base class boost for multi-class classification.
, Mark Palatucci
, Jian Zhang
: Blockwise coordinate descent procedures for the multi-task lasso, with applications to neural semantic basis discovery.
: Proto-predictive representation of states with simple recurrent temporal-difference networks.
: A simpler unified analysis of budget perceptrons.
, András Lörincz
: Optimistic initialization and greediness lead to polynomial time learning in factored MDPs.
Robert E. Tillman
: Structure learning with independent non-identically distributed data.
: Robot trajectory optimization using approximate inference.
: Herding dynamical weights to learn.
: Invited talk: Can learning kernels help performance?
: Invited talk: Drifting games, boosting and online learning.
: Workshop summary: Abstraction in reinforcement learning.
, Kai Yu
: Tutorial summary: Learning with dependencies between several response variables.
: Tutorial summary: The neuroscience of reinforcement learning.
: Tutorial summary: Large social and information networks: opportunities for ML.
Noah A. Smith
: Tutorial summary: Structured prediction for natural language processing.