Yishay Mansour

Learning Conditional Averages COLT 2026 Learning from Equivalence Queries, Revisited COLT 2026 The Hidden Cost of Approximation in Online Mirror Descent COLT 2026 The Sample Complexity of Multiclass and Sparse Contextual Bandits COLT 2026 A Fine-grained Characterization of PAC Learnability COLT 2025 Batch Ensemble for Variance Dependent Regret in Stochastic Bandits AAAI 2025 Convergence of Policy Mirror Descent Beyond Compatible Function Approximation ICML 2025 Delay as Payoff in MAB AAAI 2025 Dueling Convex Optimization with General Preferences ICML 2025 Near-optimal Regret Using Policy Optimization in Online MDPs with Aggregate Bandit Feedback ICML 2025 Non-stochastic Bandits With Evolving Observations ALT 2025 Of Dice and Games: A Theory of Generalized Boosting COLT 2025 Rate-Preserving Reductions for Blackwell Approachability COLT 2025 A Theory of Interpretable Approximations COLT 2024 Eluder-based Regret for Stochastic Contextual MDPs ICML 2024 Faster Convergence with MultiWay Preferences AISTATS 2024 Fast Rates for Bandit PAC Multiclass Classification NeurIPS 2024 How to Boost Any Loss Function NeurIPS 2024 Learnability Gaps of Strategic Classification COLT 2024 Learning-Augmented Algorithms with Explicit Predictors NeurIPS 2024 Partially Interpretable Models with Guarantees on Coverage and Accuracy ALT 2024 Principal-Agent Reward Shaping in MDPs AAAI 2024 Rate-Optimal Policy Optimization for Linear Markov Decision Processes ICML 2024 The Real Price of Bandit Information in Multiclass Classification COLT 2024 Black-Box Differential Privacy for Interactive ML NeurIPS 2023 Concurrent Shuffle Differential Privacy Under Continual Observation ICML 2023 Efficient Rate Optimal Regret for Adversarial Contextual MDPs Using Online Function Approximation ICML 2023 Eliciting User Preferences for Personalized Multi-Objective Decision Making through Comparative Feedback NeurIPS 2023 Finding Safe Zones of Markov Decision Processes Policies NeurIPS 2023 Improved Regret for Efficient Online Reinforcement Learning with Linear Function Approximation ICML 2023 Learning Revenue Maximization Using Posted Prices for Stochastic Strategic Patient Buyers AAAI 2023 Multiclass Boosting: Simple and Intuitive Weak Learning Criteria NeurIPS 2023 Optimism in Face of a Context:Regret Guarantees for Stochastic Contextual MDP AAAI 2023 Pseudonorm Approachability and Applications to Regret Minimization ALT 2023 Random Classification Noise does not defeat All Convex Potential Boosters Irrespective of Model Choice ICML 2023 Regret Minimization and Convergence to Equilibria in General-sum Markov Games ICML 2023 Reinforcement Learning Can Be More Efficient with Multiple Rewards ICML 2023 A Characterization of Semi-Supervised Adversarially Robust PAC Learnability NeurIPS 2022 Benign Underfitting of Stochastic Gradient Descent NeurIPS 2022 Cooperative Online Learning in Stochastic and Adversarial MDPs ICML 2022 Fair Wrapping for Black-box Predictions NeurIPS 2022 FriendlyCore: Practical Differentially Private Aggregation ICML 2022 Guarantees for Epsilon-Greedy Reinforcement Learning with Function Approximation ICML 2022 Improved Generalization Bounds for Adversarially Robust Learning JMLR 2022 Learning Adversarial Markov Decision Processes with Delayed Feedback AAAI 2022 Modeling Attrition in Recommender Systems with Departing Bandits AAAI 2022 Monotone Learning COLT 2022 Near-Optimal Regret for Adversarial MDP with Delayed Bandit Feedback NeurIPS 2022 Nonstochastic Bandits with Composite Anonymous Feedback JMLR 2022 Strategizing against Learners in Bayesian Games COLT 2022 Adversarial Dueling Bandits ICML 2021 Agnostic Reinforcement Learning with Low-Rank MDPs and Rich Observations NeurIPS 2021 A Theory of Multiple-Source Adaptation with Limited Target Labeled Data AISTATS 2021 Differentially-Private Clustering of Easy Instances ICML 2021 Differentially Private Multi-Armed Bandits in the Shuffle Model NeurIPS 2021 Dueling Bandits with Team Comparisons NeurIPS 2021 Dueling Convex Optimization ICML 2021 Minimax Regret for Stochastic Shortest Path NeurIPS 2021 Online Markov Decision Processes with Aggregate Bandit Feedback COLT 2021 Optimal Rates for Random Order Online Optimization NeurIPS 2021 Oracle-Efficient Regret Minimization in Factored MDPs with Unknown Structure NeurIPS 2021 ROI Maximization in Stochastic Online Decision-Making NeurIPS 2021 Stochastic Multi-Armed Bandits with Unrestricted Delay Distributions ICML 2021 Stochastic Shortest Path with Adversarially Changing Costs IJCAI 2021 The Sparse Vector Technique, Revisited COLT 2021 Adversarially Robust Streaming Algorithms via Differential Privacy NeurIPS 2020 Apprenticeship Learning via Frank-Wolfe AAAI 2020 Designing Committees for Mitigating Biases AAAI 2020 Near-optimal Regret Bounds for Stochastic Shortest Path ICML 2020 Online Revenue Maximization for Server Pricing IJCAI 2020 Planning in Hierarchical Reinforcement Learning: Guarantees for Using Local Policies ALT 2020 Prediction with Corrupted Expert Advice NeurIPS 2020 Private Learning of Halfspaces: Simplifying the Construction and Reducing the Sample Complexity NeurIPS 2020 Privately Learning Thresholds: Closing the Exponential Gap COLT 2020 Reinforcement Learning with Feedback Graphs NeurIPS 2020 Sample Complexity of Uniform Convergence for Multicalibration NeurIPS 2020 Thompson Sampling for Adversarial Bit Prediction ALT 2020 Top-k Combinatorial Bandits with Full-Bandit Feedback ALT 2020 Unknown mixing times in apprenticeship and reinforcement learning UAI 2020 Adversarial Online Learning with noise ICML 2019 Competitive ratio vs regret minimization: achieving the best of both worlds ALT 2019 Delay and Cooperation in Nonstochastic Bandits JMLR 2019 Differentially Private Learning of Geometric Concepts ICML 2019 Graph-based Discriminators: Sample Complexity and Expressiveness NeurIPS 2019 Improved Generalization Bounds for Robust Learning ALT 2019 Individual Regret in Cooperative Nonstochastic Multi-Armed Bandits NeurIPS 2019 Learning Linear-Quadratic Regulators Efficiently with only √T Regret ICML 2019 Learning to Screen NeurIPS 2019 Online Convex Optimization in Adversarial Markov Decision Processes ICML 2019 Online Stochastic Shortest Path with Bandit Feedback and Unknown Transition Function NeurIPS 2019 Discriminative Learning of Prediction Intervals AISTATS 2018 Learning Decision Trees with Stochastic Linear Classifiers ALT 2018 Nonstochastic Bandits with Composite Anonymous Feedback COLT 2018 Online Linear Quadratic Control ICML 2018 Planning and Learning with Stochastic Action Sets IJCAI 2018 Robust Inference for Multiclass Classification ALT 2018 Bandits with Movement Costs and Adaptive Pricing COLT 2017 Efficient Co-Training of Linear Separators under Weak Dependence COLT 2017 Efficient PAC Learning from the Crowd COLT 2017 Multi-Armed Bandits with Metric Movement Costs NeurIPS 2017 Submultiplicative Glivenko-Cantelli and Uniform Convergence of Revenues NeurIPS 2017 Delay and Cooperation in Nonstochastic Bandits COLT 2016 Online Learning with Low Rank Experts COLT 2016 Online Pricing with Strategic and Patient Buyers NeurIPS 2016 Classification with Low Rank and Missing Data ICML 2015 Learning and inference in the presence of corrupted inputs COLT 2015 On the Complexity of Learning with Kernels COLT 2015 Thompson Sampling for Complex Online Problems ICML 2014 Exploiting Ontology Structures and Unlabeled Data for Learning ICML 2013 From Bandits to Experts: A Tale of Domination and Independence NeurIPS 2013 Regret Minimization for Branching Experts COLT 2013 Distributed Learning, Communication Complexity and Privacy COLT 2012 Learning Multiple Tasks using Shared Hypotheses NeurIPS 2012 Learning Bounds for Importance Weighting NeurIPS 2010 Domain Adaptation with Multiple Sources NeurIPS 2008 From External to Internal Regret JMLR 2007 Action Elimination and Stopping Conditions for the Multi-Armed Bandit and Reinforcement Learning Problems JMLR 2006 Concentration Bounds for Unigram Language Models JMLR 2005 Learning Rates for Q-learning JMLR 2003