Yishay Mansour

Regret Bounds for Adversarial Contextual Bandits with General Function Approximation and Delayed Feedback

Improved Best-of-Both-Worlds Regret for Bandits with Delayed Feedback

Near-optimal Regret Using Policy Optimization in Online MDPs with Aggregate Bandit Feedback

Principled Model Routing for Unknown Mixtures of Source Domains

Individual Regret in Cooperative Stochastic Multi-Armed Bandits

Convergence of Policy Mirror Descent Beyond Compatible Function Approximation

Probably Approximately Precision and Recall Learning

Dueling Convex Optimization with General Preferences

Fast Rates for Bandit PAC Multiclass Classification

How to Boost Any Loss Function

Learning-Augmented Algorithms with Explicit Predictors

Optimal Rates for Convex Optimization with Multiway Preferences