Lune

Profiles2020-2026

Haipeng Luo

University of Southern California

35Papers
12Last author
40Unique co-authors
4First author
0Solo

First and last author come from byline position, which some venues assign alphabetically.

Recent papers35

  1. Proximal Regret and Proximal Correlated Equilibria: A New Tractable Solution Concept for Online Learning and GamesAuthor 3 of 5STOC 2026 · 5 citations
  2. Simultaneous Swap Regret Minimization via KL-CalibrationAuthor 1 of 3NeurIPS 2025 · 13 citations
  3. From Average-Iterate to Last-Iterate Convergence in Games: A Reduction and Its ApplicationsAuthor 2 of 4NeurIPS 2025 · 9 citations
  4. Improved Bounds for Swap Multicalibration and Swap OmnipredictionAuthor 1 of 3NeurIPS 2025 · 5 citations
  5. Improved Regret and Contextual Linear Extension for Pandora's Box and Prophet InequalityAuthor 4 of 5NeurIPS 2025 · 5 citations
  6. Comparator-Adaptive Φ-Regret: Improved Bounds, Simpler Algorithms, and Applications to GamesAuthor 3 of 4NeurIPS 2025 · 4 citations
  7. Adapting to Stochastic and Adversarial Losses in Episodic MDPs with Aggregate Bandit FeedbackAuthor 3 of 5NeurIPS 2025 · 2 citations
  8. Last-Iterate Convergence Properties of Regret-Matching Algorithms in GamesAuthor 5 of 6ICLR 2025
  9. Fast Last-Iterate Convergence of Learning in Games Requires Forgetful AlgorithmsAuthor 5 of 6NeurIPS 2024 · 24 citations
  10. Optimal Multiclass U-Calibration Error and BeyondAuthor 1 of 3NeurIPS 2024 · 15 citations
  11. No-Regret Learning for Fair Multi-Agent Social Welfare OptimizationAuthor 4 of 4NeurIPS 2024 · 7 citations
  12. Contextual Multinomial Logit Bandits with General Value FunctionsAuthor 2 of 2NeurIPS 2024 · 5 citations
  13. Provably Efficient Interactive-Grounded Learning with Personalized RewardAuthor 3 of 4NeurIPS 2024 · 3 citations
  14. On Tractable Φ-Equilibria in Non-Concave GamesAuthor 3 of 5NeurIPS 2024
  15. Uncoupled and Convergent Learning in Two-Player Zero-Sum Markov Games with Bandit FeedbackAuthor 2 of 4NeurIPS 2023 · 31 citations
  16. Improved Best-of-Both-Worlds Guarantees for Multi-Armed Bandits: FTRL with General Regularizers and Multiple Optimal ArmsAuthor 3 of 3NeurIPS 2023 · 24 citations
  17. Regret Matching+: (In)Stability and Fast Convergence in GamesAuthor 4 of 4NeurIPS 2023 · 22 citations
  18. Refined Regret for Adversarial MDPs with Linear Function ApproximationAuthor 2 of 4ICML 2023 · 15 citations
  19. No-Regret Online Reinforcement Learning with Adversarial Losses and TransitionsAuthor 6 of 6NeurIPS 2023 · 14 citations
  20. Practical Contextual Bandits with Feedback GraphsAuthor 4 of 5NeurIPS 2023 · 11 citations
  21. Uncoupled Learning Dynamics with O(log T) Swap Regret in Multiplayer GamesAuthor 5 of 6NeurIPS 2022 · 51 citations
  22. Near-Optimal No-Regret Learning Dynamics for General Convex GamesAuthor 3 of 6NeurIPS 2022 · 43 citations
  23. Kernelized Multiplicative Weights for 0/1-Polyhedral Games: Bridging the Gap Between Learning in Extensive-Form and Normal-Form GamesAuthor 3 of 4ICML 2022 · 35 citations
  24. Near-Optimal Regret for Adversarial MDP with Delayed Bandit FeedbackAuthor 3 of 5NeurIPS 2022 · 29 citations
  25. Follow-the-Perturbed-Leader for Adversarial Markov Decision Processes with Bandit FeedbackAuthor 2 of 3NeurIPS 2022 · 22 citations
  26. Near-Optimal Goal-Oriented Reinforcement Learning in Non-Stationary EnvironmentsAuthor 2 of 2NeurIPS 2022 · 10 citations
  27. Linear Last-iterate Convergence in Constrained Saddle-point OptimizationAuthor 4 of 4ICLR 2021 · 146 citations
  28. Policy Optimization in Adversarial MDPs: Improved Exploration via Dilated BonusesAuthor 1 of 2NeurIPS 2021 · 59 citations
  29. Last-iterate Convergence in Extensive-Form GamesAuthor 3 of 3NeurIPS 2021 · 57 citations
  30. The best of both worlds: stochastic and adversarial episodic MDPs with unknown transitionAuthor 3 of 3NeurIPS 2021 · 51 citations

Showing the 30 most recent indexed papers.

Dusk over the sea between two cliffs drawn in fine vertical lines