Yishay Mansour

40

Papers

65

Total Citations

Papers (40)

Online Pricing with Strategic and Patient Buyers

Multi-Armed Bandits with Metric Movement Costs

NeurIPS 2017arXiv

Submultiplicative Glivenko-Cantelli and Uniform Convergence of Revenues

NeurIPS 2017arXiv

Probably Approximately Precision and Recall Learning

Delay as Payoff in MAB

Batch Ensemble for Variance Dependent Regret in Stochastic Bandits

Eluder-based Regret for Stochastic Contextual MDPs

Principal-Agent Reward Shaping in MDPs

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

Rate-Optimal Policy Optimization for Linear Markov Decision Processes

Optimal Rates for Random Order Online Optimization

ROI Maximization in Stochastic Online Decision-Making

Oracle-Efficient Regret Minimization in Factored MDPs with Unknown Structure

Agnostic Reinforcement Learning with Low-Rank MDPs and Rich Observations

Dueling Bandits with Team Comparisons

Differentially Private Multi-Armed Bandits in the Shuffle Model

Minimax Regret for Stochastic Shortest Path

Benign Underfitting of Stochastic Gradient Descent

Fair Wrapping for Black-box Predictions

A Characterization of Semi-Supervised Adversarially Robust PAC Learnability

Near-Optimal Regret for Adversarial MDP with Delayed Bandit Feedback

Multiclass Boosting: Simple and Intuitive Weak Learning Criteria

Eliciting User Preferences for Personalized Multi-Objective Decision Making through Comparative Feedback

Finding Safe Zones of Markov Decision Processes Policies

Black-Box Differential Privacy for Interactive ML

Classification with Low Rank and Missing Data

Online Linear Quadratic Control

Learning Linear-Quadratic Regulators Efficiently with only $\sqrtT$ Regret

Differentially Private Learning of Geometric Concepts

Adversarial Online Learning with noise

Online Convex Optimization in Adversarial Markov Decision Processes

Learning to Screen

Individual Regret in Cooperative Nonstochastic Multi-Armed Bandits

Online Stochastic Shortest Path with Bandit Feedback and Unknown Transition Function

Graph-based Discriminators: Sample Complexity and Expressiveness

Adversarially Robust Streaming Algorithms via Differential Privacy

Sample Complexity of Uniform Convergence for Multicalibration

Private Learning of Halfspaces: Simplifying the Construction and Reducing the Sample Complexity

Prediction with Corrupted Expert Advice

Reinforcement Learning with Feedback Graphs