Peter Bartlett

Latest

• Contextual Bandits with Stage-wise Constraints
• Parallelizing Contextual Bandits
• An Instance-Dependent Analysis for the Cooperative Multi-Player Multi-Armed Bandit
• Joint Representation Training in Sequential Tasks with Shared Structure
• Parallelizing Contextual Linear Bandits
• Stochastic Bandits with Linear Constraints
• Near Optimal Policy Optimization via REPS
• Accelerated Message Passing for Entropy-Regularized MAP Inference
• On Approximate Thompson Sampling with Langevin Algorithms
• Gen-Oja: A Two-time-scale approach for Streaming CCA