Haipeng Luo

Adversarial Learning in Games with Bandit Feedback: Logarithmic Pure-Strategy Maximin Regret COLT 2026 Calibeating Made Simple COLT 2026 Efficient Swap Multicalibration of Elicitable Properties COLT 2026 Online Learning for Uninformed Markov Games: Empirical Nash-Value Regret and Non-Stationarity Adaptation COLT 2026 Swap Regret Minimization Through Response-Based Approachability COLT 2026 Toward Simultaneously Optimal Regret in U-Calibration COLT 2026 Alternating Regret for Online Convex Optimization COLT 2025 Contextual Linear Bandits with Delay as Payoff ICML 2025 Corrupted Learning Dynamics in Games COLT 2025 Instance-Dependent Regret Bounds for Learning Two-Player Zero-Sum Games with Bandit Feedback COLT 2025 Last-Iterate Convergence Properties of Regret-Matching Algorithms in Games ICLR 2025 WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct ICLR 2025 ACPO: A Policy Optimization Algorithm for Average MDPs with Constraints ICML 2024 Contextual Multinomial Logit Bandits with General Value Functions NeurIPS 2024 Efficient Contextual Bandits with Uninformed Feedback Graphs ICML 2024 Fast Last-Iterate Convergence of Learning in Games Requires Forgetful Algorithms NeurIPS 2024 Near-Optimal Policy Optimization for Correlated Equilibrium in General-Sum Markov Games AISTATS 2024 Near-Optimal Regret in Linear MDPs with Aggregate Bandit Feedback ICML 2024 No-Regret Learning for Fair Multi-Agent Social Welfare Optimization NeurIPS 2024 Online Learning in Contextual Second-Price Pay-Per-Click Auctions AISTATS 2024 On Tractable Φ-Equilibria in Non-Concave Games NeurIPS 2024 Optimal Multiclass U-Calibration Error and Beyond NeurIPS 2024 Provably Efficient Interactive-Grounded Learning with Personalized Reward NeurIPS 2024 WizardArena: Post-training Large Language Models via Simulated Offline Chatbot Arena NeurIPS 2024 Bidirectional Cross-Modal Knowledge Exploration for Video Recognition With Pre-Trained Vision-Language Models CVPR 2023 Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval? CVPR 2023 Improved Best-of-Both-Worlds Guarantees for Multi-Armed Bandits: FTRL with General Regularizers and Multiple Optimal Arms NeurIPS 2023 Improved High-Probability Regret for Adversarial Bandits with Time-Varying Feedback Graphs ALT 2023 No-Regret Learning in Two-Echelon Supply Chain with Unknown Demand Distribution AISTATS 2023 No-Regret Online Reinforcement Learning with Adversarial Losses and Transitions NeurIPS 2023 Posterior sampling-based online learning for the stochastic shortest path model UAI 2023 Practical Contextual Bandits with Feedback Graphs NeurIPS 2023 Refined Regret for Adversarial MDPs with Linear Function Approximation ICML 2023 Regret Matching+: (In)Stability and Fast Convergence in Games NeurIPS 2023 Uncoupled and Convergent Learning in Two-Player Zero-Sum Markov Games with Bandit Feedback NeurIPS 2023 Adaptive Bandit Convex Optimization with Heterogeneous Curvature COLT 2022 Corralling a Larger Band of Bandits: A Case Study on Switching Regret for Linear Bandits COLT 2022 Follow-the-Perturbed-Leader for Adversarial Markov Decision Processes with Bandit Feedback NeurIPS 2022 Improved No-Regret Algorithms for Stochastic Shortest Path with Linear MDP ICML 2022 Kernelized Multiplicative Weights for 0/1-Polyhedral Games: Bridging the Gap Between Learning in Extensive-Form and Normal-Form Games ICML 2022 Learning Infinite-horizon Average-reward Markov Decision Process with Constraints ICML 2022 Near-Optimal Goal-Oriented Reinforcement Learning in Non-Stationary Environments NeurIPS 2022 Near-Optimal No-Regret Learning Dynamics for General Convex Games NeurIPS 2022 Near-Optimal Regret for Adversarial MDP with Delayed Bandit Feedback NeurIPS 2022 No-Regret Learning in Time-Varying Zero-Sum Games ICML 2022 Policy Optimization for Stochastic Shortest Path COLT 2022 Uncoupled Learning Dynamics with $O(\log T)$ Swap Regret in Multiplayer Games NeurIPS 2022 Achieving Near Instance-Optimality and Minimax-Optimality in Stochastic and Adversarial Linear Bandits Simultaneously ICML 2021 Active Online Learning with Hidden Shifting Domains AISTATS 2021 Adversarial Online Learning with Changing Action Sets: Efficient Algorithms with Approximate Regret Bounds ALT 2021 Finding the Stochastic Shortest Path with Low Regret: the Adversarial Cost and Unknown Transition Case ICML 2021 Implicit Finite-Horizon Approximation and Efficient Optimal Algorithms for Stochastic Shortest Path NeurIPS 2021 Impossible Tuning Made Possible: A New Expert Algorithm and Its Applications COLT 2021 Last-iterate Convergence in Extensive-Form Games NeurIPS 2021 Last-iterate Convergence of Decentralized Optimistic Gradient Descent/Ascent in Infinite-horizon Competitive Markov Games COLT 2021 Learning Infinite-horizon Average-reward MDPs with Linear Function Approximation AISTATS 2021 Linear Last-iterate Convergence in Constrained Saddle-point Optimization ICLR 2021 Minimax Regret for Stochastic Shortest Path with Adversarial Costs and Known Transition COLT 2021 Non-stationary Reinforcement Learning without Prior Knowledge: an Optimal Black-box Approach COLT 2021 Policy Optimization in Adversarial MDPs: Improved Exploration via Dilated Bonuses NeurIPS 2021 The best of both worlds: stochastic and adversarial episodic MDPs with unknown transition NeurIPS 2021 A Closer Look at Small-loss Bounds for Bandits with Graph Feedback COLT 2020 Bias no more: high-probability data-dependent regret bounds for adversarial bandits and MDPs NeurIPS 2020 Comparator-Adaptive Convex Bandits NeurIPS 2020 Fair Contextual Multi-Armed Bandits: Theory and Experiments UAI 2020 Learning Adversarial Markov Decision Processes with Bandit Feedback and Unknown Transition ICML 2020 Model-free Reinforcement Learning in Infinite-horizon Average-reward Markov Decision Processes ICML 2020 Open Problem: Model Selection for Contextual Bandits COLT 2020 Simultaneously Learning Stochastic and Adversarial Episodic MDPs with Known Transition NeurIPS 2020 Taking a hint: How to leverage loss predictors in contextual bandits? COLT 2020 Achieving Optimal Dynamic Regret for Non-stationary Bandits without Prior Information COLT 2019 A New Algorithm for Non-stationary Contextual Bandits: Efficient, Optimal and Parameter-free COLT 2019 Beating Stochastic and Adversarial Semi-bandits Optimally and Simultaneously ICML 2019 Equipping Experts/Bandits with Long-term Memory NeurIPS 2019 Hypothesis Set Stability and Generalization NeurIPS 2019 Improved Path-length Regret Bounds for Bandits COLT 2019 Model Selection for Contextual Bandits NeurIPS 2019 Efficient Contextual Bandits in Non-stationary Worlds COLT 2018 Efficient Online Portfolio with Logarithmic Regret NeurIPS 2018 Logistic Regression: The Importance of Being Improper COLT 2018 More Adaptive Algorithms for Adversarial Bandits COLT 2018 Practical Contextual Bandits with Regression Oracles ICML 2018 Corralling a Band of Bandit Algorithms COLT 2017 Open Problem: First-Order Regret Bounds for Contextual Bandits COLT 2017 Efficient Second Order Online Learning by Sketching NeurIPS 2016 Improved Regret Bounds for Oracle-Based Adversarial Contextual Bandits NeurIPS 2016 Optimal and Adaptive Algorithms for Online Boosting IJCAI 2016 Variance-Reduced and Projection-Free Stochastic Optimization ICML 2016 Achieving All with No Parameters: AdaNormalHedge COLT 2015 Fast Convergence of Regularized Learning in Games NeurIPS 2015 Online Gradient Boosting NeurIPS 2015 Optimal and Adaptive Algorithms for Online Boosting ICML 2015 A Drifting-Games Analysis for Online Learning and Applications to Boosting NeurIPS 2014 Towards Minimax Online Learning with Unknown Time Horizon ICML 2014