S
Sham M. Kakade
Researcher at University of Washington
Publications - 310
Citations - 29957
Sham M. Kakade is an academic researcher from University of Washington. The author has contributed to research in topics: Reinforcement learning & Stochastic gradient descent. The author has an hindex of 80, co-authored 289 publications receiving 24868 citations. Previous affiliations of Sham M. Kakade include University of Pennsylvania & Amazon.com.
Papers
More filters
Proceedings Article
Gaussian Process Optimization in the Bandit Setting: No Regret and Experimental Design
TL;DR: This work analyzes GP-UCB, an intuitive upper-confidence based algorithm, and bound its cumulative regret in terms of maximal information gain, establishing a novel connection between GP optimization and experimental design and obtaining explicit sublinear regret bounds for many commonly used covariance functions.
Proceedings Article
A Natural Policy Gradient
TL;DR: This work provides a natural gradient method that represents the steepest descent direction based on the underlying structure of the parameter space and shows drastic performance improvements in simple MDPs and in the more challenging MDP of Tetris.
Proceedings ArticleDOI
Cover trees for nearest neighbor
TL;DR: A tree data structure for fast nearest neighbor operations in general n-point metric spaces (where the data set consists of n points) that shows speedups over the brute force search varying between one and several orders of magnitude on natural machine learning datasets.
Journal ArticleDOI
Information-Theoretic Regret Bounds for Gaussian Process Optimization in the Bandit Setting
TL;DR: This work analyzes an intuitive Gaussian process upper confidence bound algorithm, and bound its cumulative regret in terms of maximal in- formation gain, establishing a novel connection between GP optimization and experimental design and obtaining explicit sublinear regret bounds for many commonly used covariance functions.
Proceedings Article
Approximately Optimal Approximate Reinforcement Learning
Sham M. Kakade,John Langford +1 more