Profiles2020-2026
Yishay Mansour
Tel Aviv University
35Papers
20Last author
40Unique co-authors
0First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers35
- A Theoretical Framework for Statistical Evaluability of Generative ModelsAuthor 2 of 4ICML 2026 · 1 citation
- Optimal Regret for Policy Optimization in Contextual BanditsAuthor 2 of 2ICML 2026 · 1 citation
- Near-Optimal Regret for Policy Optimization in Contextual MDPs with General Offline Function ApproximationAuthor 4 of 4ICML 2026
- Probably Approximately Precision and Recall LearningAuthor 2 of 4NeurIPS 2025 · 8 citations
- Delay as Payoff in MABAuthor 4 of 4AAAI 2025 · 5 citations
- Regret Bounds for Adversarial Contextual Bandits with General Function Approximation and Delayed FeedbackAuthor 4 of 4NeurIPS 2025 · 5 citations
- Batch Ensemble for Variance Dependent Regret in Stochastic BanditsAuthor 3 of 3AAAI 2025 · 3 citations
- Improved Best-of-Both-Worlds Regret for Bandits with Delayed FeedbackAuthor 4 of 4NeurIPS 2025 · 2 citations
- Dueling Convex Optimization with General PreferencesAuthor 3 of 3ICML 2025
- Near-optimal Regret Using Policy Optimization in Online MDPs with Aggregate Bandit FeedbackAuthor 4 of 4ICML 2025
- Principal-Agent Reward Shaping in MDPsAuthor 2 of 4AAAI 2024 · 21 citations
- Rate-Optimal Policy Optimization for Linear Markov Decision ProcessesAuthor 4 of 4ICML 2024 · 11 citations
- Eluder-based Regret for Stochastic Contextual MDPsAuthor 4 of 4ICML 2024 · 10 citations
- Improved Regret for Efficient Online Reinforcement Learning with Linear Function ApproximationAuthor 3 of 3ICML 2023 · 15 citations
- Optimism in Face of a Context: Regret Guarantees for Stochastic Contextual MDPAuthor 2 of 2AAAI 2023 · 13 citations
- Efficient Rate Optimal Regret for Adversarial Contextual MDPs Using Online Function ApproximationAuthor 4 of 4ICML 2023 · 10 citations
- Eliciting User Preferences for Personalized Multi-Objective Decision Making through Comparative FeedbackAuthor 4 of 6NeurIPS 2023 · 10 citations
- Black-Box Differential Privacy for Interactive MLAuthor 2 of 5NeurIPS 2023 · 7 citations
- Concurrent Shuffle Differential Privacy Under Continual ObservationAuthor 3 of 4ICML 2023 · 3 citations
- Learning Revenue Maximization Using Posted Prices for Stochastic Strategic Patient BuyersAuthor 3 of 3AAAI 2023 · 2 citations
- Learning Adversarial Markov Decision Processes with Delayed FeedbackAuthor 3 of 3AAAI 2022 · 40 citations
- FriendlyCore: Practical Differentially Private AggregationAuthor 4 of 5ICML 2022 · 39 citations
- Near-Optimal Regret for Adversarial MDP with Delayed Bandit FeedbackAuthor 4 of 5NeurIPS 2022 · 29 citations
- Benign Underfitting of Stochastic Gradient DescentAuthor 3 of 4NeurIPS 2022 · 26 citations
- A Characterization of Semi-Supervised Adversarially Robust PAC LearnabilityAuthor 3 of 3NeurIPS 2022 · 19 citations
- Dynamic algorithms against an adaptive adversary: generic constructions and lower boundsAuthor 3 of 6STOC 2022 · 11 citations
- Differentially Private Multi-Armed Bandits in the Shuffle ModelAuthor 3 of 4NeurIPS 2021 · 37 citations
- Adversarial Dueling BanditsAuthor 3 of 3ICML 2021 · 35 citations
- Differentially-Private Clustering of Easy InstancesAuthor 3 of 5ICML 2021 · 27 citations
- Optimal Rates for Random Order Online OptimizationAuthor 3 of 3NeurIPS 2021 · 13 citations
Showing the 30 most recent indexed papers.
