HL
Haipeng Luo
cs.LGstat.MLcs.GTcs.AImath.OCcs.CLcs.CVcs.DSNeurorehabilitationrehabilitation medicine and physical therapy
On Valency
published · living versionsW_xqzef2sa·v1 · currentpublished
Fast Convergence of Regularized Learning in Games
with Vasilis Syrgkanis, Alekh Agarwal, Robert E. Schapire
1 version
Preprints & journals
104 papers in the corpus · 2013–2026Near-Optimal Last-Iterate Convergence for Zero-Sum Games with Bandit Feedback and Opponent Actions2605.09363v1 · Soumita Hait, Ping Li, Haipeng Luo et al.2026 · 0 citationsarXiv
A Short Note on a Variant of the Squint Algorithm2603.03409v1 · Haipeng Luo2026 · 0 citationsarXiv
Scale-Invariant Fast Convergence in Games2602.11857v1 · Taira Tsuchiya, Haipeng Luo, Shinji Ito2026 · 0 citationsarXiv
Is Online Linear Optimization Sufficient for Strategic Robustness?2602.12253v1 · Yang Cai, Haipeng Luo, Chen-Yu Wei et al.2026 · 0 citationsarXiv
Adversarial Learning in Games with Bandit Feedback: Logarithmic Pure-Strategy Maximin Regret2602.06348v1 · Shinji Ito, Haipeng Luo, Arnab Maiti et al.2026 · 0 citationsarXiv
Online Learning for Uninformed Markov Games: Empirical Nash-Value Regret and Non-Stationarity Adaptation2602.07205v1 · Junyan Liu, Haipeng Luo, Zihan Zhang et al.2026 · 0 citationsarXiv
Swap Regret Minimization Through Response-Based Approachability2602.06264v3 · Ioannis Anagnostides, Gabriele Farina, Maxwell Fishelson et al.2026 · 1 citationarXiv
AgentMath: Empowering Mathematical Reasoning for Large Language Models via Tool-Augmented Agent2512.20745v3 · Haipeng Luo, Huawen Feng, Qingfeng Sun et al.2025 · 0 citationsarXiv
Towards AI-based precision rehabilitation via contextual model-based reinforcement learning.41419889 · Ye, Dongze, Luo, Haipeng, Winstein, Carolee et al.2025 · 18 citationsJournal of neuroengineering and rehabilitation. 2025;22(1):263
Proximal Regret and Proximal Correlated Equilibria: A New Tractable Solution Concept for Online Learning and Games2511.01852v2 · Yang Cai, Constantinos Daskalakis, Haipeng Luo et al.2025 · 0 citationsarXiv
Adapting to Stochastic and Adversarial Losses in Episodic MDPs with Aggregate Bandit Feedback2510.17103v2 · Shinji Ito, Kevin Jamieson, Haipeng Luo et al.2025 · 0 citationsarXiv
Analysis and forecast of hand, foot, and mouth disease epidemic trends in Guangzhou, China, 2013-2023.41026757 · Luo, Haipeng, Zhong, Siyi, Liu, Jiaojiao et al.2025 · 0 citationsPloS one. 2025;20(9):e0333544
From Dueling Bandits to Episodic MDPs: Learning with Adversarial Preference Feedback2507.11706v2 · Taira Tsuchiya, Shinji Ito, Haipeng Luo2025 · 0 citationsarXiv
From Average-Iterate to Last-Iterate Convergence in Games: A Reduction and Its Applications2506.03464v2 · Yang Cai, Haipeng Luo, Chen-Yu Wei et al.2025 · 0 citationsarXiv
Improved Regret and Contextual Linear Extension for Pandora's Box and Prophet Inequality2505.18828v2 · Junyan Liu, Ziyun Chen, Kun Wang et al.2025 · 1 citationarXiv
Comparator-Adaptive -Regret: Improved Bounds, Simpler Algorithms, and Applications to Games2505.17277v2 · Soumita Hait, Ping Li, Haipeng Luo et al.2025 · 0 citationsarXiv
Group Distributionally Robust Optimization with Flexible Sample Queries2505.15212v1 · Haomin Bai, Dingzhi Yu, Shuai Li et al.2025 · 0 citationsarXiv
On Separation Between Best-Iterate, Random-Iterate, and Last-Iterate Convergence of Learning in Games2503.02825v1 · Yang Cai, Gabriele Farina, Julien Grand-Cl'ement et al.2025 · 0 citationsarXiv
Instance-Dependent Regret Bounds for Learning Two-Player Zero-Sum Games with Bandit Feedback2502.17625v1 · Shinji Ito, Haipeng Luo, Taira Tsuchiya et al.2025 · 0 citationsarXiv
Contextual Linear Bandits with Delay as Payoff2502.12528v2 · Mengxiao Zhang, Yingfei Wang, Haipeng Luo2025 · 0 citationsarXiv
Alternating Regret for Online Convex Optimization2502.12529v2 · Soumita Hait, Ping Li, Haipeng Luo et al.2025 · 0 citationsarXiv
Corrupted Learning Dynamics in Games2412.07120v2 · Taira Tsuchiya, Shinji Ito, Haipeng Luo2024 · 0 citationsarXiv
Arena Learning: Build Data Flywheel for LLMs Post-training via Simulated Chatbot Arena2407.10627v1 · Haipeng Luo, Qingfeng Sun, Can Xu et al.2024 · 2 citationsarXiv
Fast Last-Iterate Convergence of Learning in Games Requires Forgetful Algorithms2406.10631v2 · Yang Cai, Gabriele Farina, Julien Grand-Cl'ement et al.2024 · 1 citationarXiv
Provably Efficient Interactive-Grounded Learning with Personalized Reward2405.20677v1 · Mengxiao Zhang, Yuheng Zhang, Haipeng Luo et al.2024 · 0 citationsarXiv
Near-Optimal Regret in Linear MDPs with Aggregate Bandit Feedback2405.07637v2 · Asaf Cassel, Haipeng Luo, Aviv Rosenberg et al.2024 · 0 citationsarXiv
On Tractable -Equilibria in Non-Concave Games2403.08171v4 · Yang Cai, Constantinos Daskalakis, Haipeng Luo et al.2024 · 0 citationsarXiv
Contextual Multinomial Logit Bandits with General Value Functions2402.08126v2 · Mengxiao Zhang, Haipeng Luo2024 · 0 citationsarXiv
Efficient Contextual Bandits with Uninformed Feedback Graphs2402.08127v1 · Mengxiao Zhang, Yuheng Zhang, Haipeng Luo et al.2024 · 0 citationsarXiv
Near-Optimal Policy Optimization for Correlated Equilibrium in General-Sum Markov Games2401.15240v2 · Yang Cai, Haipeng Luo, Chen-Yu Wei et al.2024 · 0 citationsarXiv
Last-Iterate Convergence Properties of Regret-Matching Algorithms in Games2311.00676v2 · Yang Cai, Gabriele Farina, Julien Grand-Cl'ement et al.2023 · 0 citationsarXiv
Online Learning in Contextual Second-Price Pay-Per-Click Auctions2310.05047v1 · Mengxiao Zhang, Haipeng Luo2023 · 0 citationsarXiv
WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct2308.09583v3 · Haipeng Luo, Qingfeng Sun, Can Xu et al.2023 · 33 citationsarXiv
Long-term forecasting of a motor outcome following rehabilitation in chronic stroke via a hierarchical bayesian dynamic model.37386512 · Schweighofer, Nicolas, Ye, Dongze, Luo, Haipeng et al.2023 · 10 citationsJournal of neuroengineering and rehabilitation. 2023;20(1):83
Regret Matching+: (In)Stability and Fast Convergence in Games2305.14709v1 · Gabriele Farina, Julien Grand-Cl'ement, Christian Kroer et al.2023 · 2 citationsarXiv
Uncoupled and Convergent Learning in Two-Player Zero-Sum Markov Games with Bandit Feedback2303.02738v2 · Yang Cai, Haipeng Luo, Chen-Yu Wei et al.2023 · 0 citationsarXiv
Improved Best-of-Both-Worlds Guarantees for Multi-Armed Bandits: FTRL with General Regularizers and Multiple Optimal Arms2302.13534v2 · Tiancheng Jin, Junyan Liu, Haipeng Luo2023 · 1 citationarXiv
ACPO: A Policy Optimization Algorithm for Average MDPs with Constraints2302.00808v4 · Akhil Agnihotri, Rahul Jain, Haipeng Luo2023 · 0 citationsarXiv
Refined Regret for Adversarial MDPs with Linear Function Approximation2301.12942v2 · Yan Dai, Haipeng Luo, Chen-Yu Wei et al.2023 · 0 citationsarXiv
Bidirectional Cross-Modal Knowledge Exploration for Video Recognition with Pre-trained Vision-Language Models2301.00182v2 · Wenhao Wu, Xiaohan Wang, Haipeng Luo et al.2022 · 130 citationsarXiv
Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval?2301.00184v3 · Wenhao Wu, Haipeng Luo, Bo Fang et al.2022 · 143 citationsarXiv
No-Regret Learning in Two-Echelon Supply Chain with Unknown Demand Distribution2210.12663v2 · Mengxiao Zhang, Shi Chen, Haipeng Luo et al.2022 · 3 citationsarXiv
Long-Term Forecasting of a Motor Outcome Following Rehabilitation in Chronic Stroke via a Hierarchical Bayesian Model of Motor Learning10.1101/2022.10.20.22280926v1 · Schweighofer, N., Ye, D., Luo, H. et al.2022 · 1 citationmedRxiv
Improved High-Probability Regret for Adversarial Bandits with Time-Varying Feedback Graphs2210.01376v2 · Haipeng Luo, Hanghang Tong, Mengxiao Zhang et al.2022 · 3 citationsarXiv
Clairvoyant Regret Minimization: Equivalence with Nemirovski's Conceptual Prox Method and Extension to General Convex Games2208.14891v1 · Gabriele Farina, Christian Kroer, Chung-Wei Lee et al.2022 · 1 citationarXiv
Near-Optimal No-Regret Learning Dynamics for General Convex Games2206.08742v3 · Gabriele Farina, Ioannis Anagnostides, Haipeng Luo et al.2022 · 6 citationsarXiv
Near-Optimal Goal-Oriented Reinforcement Learning in Non-Stationary Environments2205.13044v1 · Liyu Chen, Haipeng Luo2022 · 0 citationsarXiv
Uncoupled Learning Dynamics with Swap Regret in Multiplayer Games2204.11417v2 · Ioannis Anagnostides, Gabriele Farina, Christian Kroer et al.2022 · 1 citationarXiv
Adaptive Bandit Convex Optimization with Heterogeneous Curvature2202.06150v1 · Haipeng Luo, Mengxiao Zhang, Peng Zhao2022 · 1 citationarXiv
Corralling a Larger Band of Bandits: A Case Study on Switching Regret for Linear Bandits2202.06151v1 · Haipeng Luo, Mengxiao Zhang, Peng Zhao et al.2022 · 0 citationsarXiv
Career total: 172 works. 104 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.