PPaperPicks

Yishay Mansour

Tel Aviv University, School of Computer Science, Israel

27 papers at tracked venues · 16 at CORE A* · active 2024–2026

DBLP profile ↗ORCID 0000-0001-6891-2645 ↗Google Scholar ↗Homepage ↗

Venues

COLT ×10NeurIPS ×8ICML ×5AAAI ×3AISTATS ×1

Frequent coauthors

Marco Bressan
DBLP profile ↗ORCID search ↗
×4
Ofir Schlisselberg
DBLP profile ↗ORCID search ↗
×3
Liad Erez
DBLP profile ↗ORCID search ↗
×3
Uri Sherman
DBLP profile ↗ORCID search ↗
×2
Aadirupa Saha
DBLP profile ↗ORCID search ↗
×2
Christoph Dann
DBLP profile ↗ORCID search ↗
×2
Lee Cohen
DBLP profile ↗ORCID search ↗
×2
Orin Levy
DBLP profile ↗ORCID search ↗
×2
Mark Braverman
DBLP profile ↗ORCID search ↗
×1
Asaf B. Cassel
DBLP profile ↗ORCID search ↗
×1
Idan Barnea
DBLP profile ↗ORCID search ↗
×1
Tal Lancewicki
DBLP profile ↗ORCID search ↗
×1

Papers

  1. Learning Conditional Averages
    COLT 2026 ·
    Marco Bressan
    DBLP profile ↗ORCID search ↗
  2. Learning from Equivalence Queries, Revisited
    COLT 2026 ·
    Mark Braverman
    DBLP profile ↗ORCID search ↗
  3. The Hidden Cost of Approximation in Online Mirror Descent
    COLT 2026 ·
    Ofir Schlisselberg
    DBLP profile ↗ORCID search ↗
  4. The Sample Complexity of Multiclass and Sparse Contextual Bandits
    COLT 2026 ·
    Liad Erez
    DBLP profile ↗ORCID search ↗
  5. A Fine-grained Characterization of PAC Learnability
    COLT 2025 ·
    Marco Bressan
    DBLP profile ↗ORCID search ↗
  6. Batch Ensemble for Variance Dependent Regret in Stochastic Bandits
    AAAI 2025 ·
    Asaf B. Cassel
    DBLP profile ↗ORCID search ↗
  7. Convergence of Policy Mirror Descent Beyond Compatible Function Approximation
    ICML 2025 ·
    Uri Sherman
    DBLP profile ↗ORCID search ↗
  8. Delay as Payoff in MAB
    AAAI 2025 ·
    Ofir Schlisselberg
    DBLP profile ↗ORCID search ↗
  9. Dueling Convex Optimization with General Preferences
    ICML 2025 ·
    Aadirupa Saha
    DBLP profile ↗ORCID search ↗
  10. Improved Best-of-Both-Worlds Regret for Bandits with Delayed Feedback
    NeurIPS 2025 ·
    Ofir Schlisselberg
    DBLP profile ↗ORCID search ↗
  11. Individual Regret in Cooperative Stochastic Multi-Armed Bandits
    NeurIPS 2025 ·
    Idan Barnea
    DBLP profile ↗ORCID search ↗
  12. Near-optimal Regret Using Policy Optimization in Online MDPs with Aggregate Bandit Feedback
    ICML 2025 ·
    Tal Lancewicki
    DBLP profile ↗ORCID search ↗
  13. Of Dice and Games: A Theory of Generalized Boosting
    COLT 2025 ·
    Marco Bressan
    DBLP profile ↗ORCID search ↗
  14. Principled Model Routing for Unknown Mixtures of Source Domains
    NeurIPS 2025 ·
    Christoph Dann
    DBLP profile ↗ORCID search ↗
  15. Probably Approximately Precision and Recall Learning
    NeurIPS 2025 ·
    Lee Cohen
    DBLP profile ↗ORCID search ↗
  16. Rate-Preserving Reductions for Blackwell Approachability
    COLT 2025 ·
    Christoph Dann
    DBLP profile ↗ORCID search ↗
  17. Regret Bounds for Adversarial Contextual Bandits with General Function Approximation and Delayed Feedback
    NeurIPS 2025 ·
    Orin Levy
    DBLP profile ↗ORCID search ↗
  18. A Theory of Interpretable Approximations
    COLT 2024 ·
    Marco Bressan
    DBLP profile ↗ORCID search ↗
  19. Eluder-based Regret for Stochastic Contextual MDPs
    ICML 2024 ·
    Orin Levy
    DBLP profile ↗ORCID search ↗
  20. Fast Rates for Bandit PAC Multiclass Classification
    NeurIPS 2024 ·
    Liad Erez
    DBLP profile ↗ORCID search ↗
  21. Faster Convergence with MultiWay Preferences
    AISTATS 2024 ·
    Aadirupa Saha
    DBLP profile ↗ORCID search ↗
  22. How to Boost Any Loss Function
    NeurIPS 2024 ·
    Richard Nock
    DBLP profile ↗ORCID search ↗
  23. Learnability Gaps of Strategic Classification
    COLT 2024 ·
    Lee Cohen
    DBLP profile ↗ORCID search ↗
  24. Learning-Augmented Algorithms with Explicit Predictors
    NeurIPS 2024 ·
    Marek Eliás
    DBLP profile ↗ORCID search ↗
  25. Principal-Agent Reward Shaping in MDPs
    AAAI 2024 ·
    Omer Ben-Porat
    DBLP profile ↗ORCID search ↗
  26. Rate-Optimal Policy Optimization for Linear Markov Decision Processes
    ICML 2024 ·
    Uri Sherman
    DBLP profile ↗ORCID search ↗
  27. The Real Price of Bandit Information in Multiclass Classification
    COLT 2024 ·
    Liad Erez
    DBLP profile ↗ORCID search ↗