Michael Jordan

Latest

• Parallelizing Contextual Bandits
• An Instance-Dependent Analysis for the Cooperative Multi-Player Multi-Armed Bandit
• Online Nonsubmodular Minimization with Delayed Costs: From Full Information to Bandit Feedback
• Parallelizing Contextual Linear Bandits
• Tactical Optimism and Pessimism for Deep Reinforcement Learning
• Accelerated Message Passing for Entropy-Regularized MAP Inference
• Learning to Score Behaviors for Guided Policy Optimization
• On Approximate Thompson Sampling with Langevin Algorithms
• Convergence Rates of Smooth Message Passing with Rounding in Entropy-Regularized MAP Inference
• Robustness Guarantees for Mode Estimation with an Application to Bandits
• Gen-Oja: A Two-time-scale approach for Streaming CCA