Chen-Yu Wei

(α-β) indicates alphabetical ordering; * indicates equal contribution.

Publications

2024

Corruption-Robust Linear Bandits: Minimax Optimality and Gap-Dependent Misspecification
(α-β) Haolin Liu, Artin Tajdini, Andrew Wagenmaker, Chen-Yu Wei
NeurIPS 2024 [arXiv]
Beating Adversarial Low-Rank MDPs with Unknown Transition and Bandit Feedback
(α-β) Haolin Liu, Zakaria Mhammedi, Chen-Yu Wei, Julian Zimmert
NeurIPS 2024
How Does Variance Shape the Regret in Contextual Bandits?
(α-β) Zeyu Jia, Jian Qian, Alexander Rakhlin, Chen-Yu Wei
NeurIPS 2024 [arXiv]
On Tractable Φ-Equilibria in Non-Concave Games
(α-β) Yang Cai, Constantinos Daskalakis, Haipeng Luo, Chen-Yu Wei, Weiqiang Zheng
NeurIPS 2024 [arXiv]
Offline Reinforcement Learning: Role of State Aggregation and Trajectory Data
(α-β) Zeyu Jia, Alexander Rakhlin, Ayush Sekhari, Chen-Yu Wei
COLT 2024 [arXiv] [video]
Near-Optimal Policy Optimization for Correlated Equilibrium in General-Sum Markov Games
(α-β) Yang Cai, Haipeng Luo, Chen-Yu Wei, Weiqiang Zheng
AISTAT 2024 (Oral) [arXiv]
Towards Optimal Regret in Adversarial Linear MDPs with Bandit Feedback
(α-β) Haolin Liu, Chen-Yu Wei, Julian Zimmert
ICLR 2024 (Spotlight) [arXiv]

2023

Bypassing the Simulator: Near-Optimal Adversarial Linear Contextual Bandits
(α-β) Haolin Liu, Chen-Yu Wei, Julian Zimmert
NeurIPS 2023 [arXiv] [video]
Last-Iterate Convergent Policy Gradient Primal-Dual Methods for Constrained MDPs
Dongsheng Ding*, Chen-Yu Wei*, Kaiqing Zhang*, Alejandro Ribeiro
NeurIPS 2023 [arXiv] [video]
No-Regret Online Reinforcement Learning with Adversarial Losses and Transitions
Tiancheng Jin*, Junyan Liu*, Chloe Rouyer, William Chang, Chen-Yu Wei, Haipeng Luo
NeurIPS 2023 [arXiv] [video]
First- and Second-Order Bounds for Adversarial Linear Contextual Bandits
Julia Olkhovskaya, Jack Mayo, Tim van Erven, Gergely Neu, Chen-Yu Wei
NeurIPS 2023 [arXiv] [video]
Uncoupled and Convergent Learning in Two-Player Zero-Sum Markov Games
(α-β) Yang Cai, Haipeng Luo, Chen-Yu Wei, Weiqiang Zheng
NeurIPS 2023 [arXiv] [video]
A Blackbox Approach to Best of Both Worlds in Bandits and Beyond
(α-β) Christoph Dann, Chen-Yu Wei, Julian Zimmert
COLT 2023 [arXiv] [slides]
Best of Both Worlds Policy Optimization
(α-β) Christoph Dann, Chen-Yu Wei, Julian Zimmert
ICML 2023 (Long Talk) [arXiv] [slides] [video]
Refined Regret for Adversarial MDPs with Linear Function Approximation
(α-β) Yan Dai, Haipeng Luo, Chen-Yu Wei, Julian Zimmert
ICML 2023 [arXiv] [slides] [video]
A Unified Algorithm for Stochastic Path Problems
(α-β) Christoph Dann, Chen-Yu Wei, Julian Zimmert
ALT 2023 [arXiv] [slides]

2022

Independent Policy Gradient for Large-Scale Markov Potential Games: Sharper Rates, Function Approximation, and Game-Agnostic Convergence
Dongsheng Ding*, Chen-Yu Wei*, Kaiqing Zhang*, Mihailo Jovanovic
ICML 2022 (Long Talk) [arXiv] [video]
Personalization Improves Privacy-Accuracy Tradeoffs in Federated Optimization
Alberto Bietti, Chen-Yu Wei, Miroslav Dudik, John Langford, Zhiwei Steven Wu
ICML 2022 [arXiv] [video]
Decentralized Cooperative Reinforcement Learning with Hierarchical Information Structure
Hsu Kao, Chen-Yu Wei, Vijay Subramanian
ALT 2022 [arXiv] [slides]
A Model Selection Approach for Corruption Robust Reinforcement Learning
Chen-Yu Wei, Christoph Dann, Julian Zimmert
ALT 2022 (Best Paper Award) [arXiv] [slides]

2021

Policy Optimization in Adversarial MDPs: Improved Exploration via Dilated Bonuses
Haipeng Luo*, Chen-Yu Wei*, Chung-Wei Lee
NeurIPS 2021 [arXiv] [slides] [slides] [video]
Achieving Near Instance-Optimality and Minimax-Optimality in Stochastic and Adversarial Linear Bandits Simultaneously
(α-β) Chung-Wei Lee, Haipeng Luo, Chen-Yu Wei, Mengxiao Zhang, Xiaojin Zhang
ICML 2021 [arXiv] [slides] [video]
Non-stationary Reinforcement Learning without Prior Knowledge: An Optimal Black-Box Approach
Chen-Yu Wei and Haipeng Luo
COLT 2021 (Best Paper Award) [arXiv] [slides] [slides] [video]
Last-iterate Convergence of Decentralized Optimistic Gradient Descent/Ascent in Infinite-Horizon Competitive Markov Games
Chen-Yu Wei, Chung-Wei Lee*, Mengxiao Zhang*, Haipeng Luo
COLT 2021 [arXiv] [slides]
Impossible Tuning Made Possible: A New Expert Algorithm and Its Applications
(α-β) Liyu Chen, Haipeng Luo, Chen-Yu Wei
COLT 2021 [arXiv] [slides]
Minimax Regret for Stochastic Shortest Path with Adversarial Costs and Known Transition
Liyu Chen, Haipeng Luo, Chen-Yu Wei
COLT 2021 [arXiv] [slides] [video]
Learning Infinite-Horizon Average-Reward MDPs with Linear Function Approximation
Chen-Yu Wei, Mehdi Jafarnia-Jahromi, Haipeng Luo, Rahul Jain
AISTAT 2021 [arXiv] [slides] [video]
Linear Last-Iterate Convergence in Constrained Saddle-Point Optimization
Chen-Yu Wei, Chung-Wei Lee, Mengxiao Zhang, Haipeng Luo
ICLR 2021 [arXiv] [code] [slides] [video]
Adversarial Online Learning with Changing Action Sets: Efficient Algorithms with Approximate Regret Bounds
Ehsan Emamjomeh-Zadeh*, Chen-Yu Wei*, Haipeng Luo, David Kempe
ALT 2021 [arXiv] [slides] [video]

2020

Bias No More: High-Probability Data-Dependent Regret Bounds for Adversarial Bandits and MDPs
(α-β) Chung-Wei Lee, Haipeng Luo, Chen-Yu Wei, Mengxiao Zhang
NeurIPS 2020 (Oral) [arXiv] [slides] [video]
Federated Residual Learning
Chen-Yu Wei, Alekh Agarwal, John Langford
NeurIPS Workshop on Scalability, Privacy, and Security in Federated Learning 2020 [arXiv]
Taking a Hint: How to Leverage Loss Predictors in Contextual Bandits?
Chen-Yu Wei, Haipeng Luo, Alekh Agarwal
COLT 2020 [arXiv] [slides] [video]
Model-free Reinforcement Learning in Infinite-Horizon Average-Reward Markov Decision Processes
Chen-Yu Wei, Mehdi Jafarnia-Jahromi, Haipeng Luo, Hiteshi Sharma, Rahul Jain
ICML 2020 [arXiv] [code] [slides] [video]

2019

Analyzing the Variance of Policy Gradient Estimators for the Linear-Quadratic Regulator
James Preiss*, Sebastien Arnold*, Chen-Yu Wei*, Marius Kloft
NeurIPS Workshop on Optimization Foundations for Reinforcement Learning 2019 [arXiv]
SoCal Machine Learning Symposium 2019 (Best Poster Award)
A New Algorithm for Non-Stationary Contextual Bandits: Efficient, Optimal, and Parameter-Free
(α-β) Yifang Chen, Chung-Wei Lee, Haipeng Luo, Chen-Yu Wei
COLT 2019 [arXiv] [a joint extended abstract with Auer, Gajane, and Ortner] [slides]
Improved Path-Length Regret Bounds for Bandits
(α-β) Sebastien Bubeck, Yuanzhi Li, Haipeng Luo, Chen-Yu Wei
COLT 2019 [arXiv] [slides]
Beating Stochastic and Adversarial Semi-Bandits Optimally and Simultaneously
Julian Zimmert, Haipeng Luo, Chen-Yu Wei
ICML 2019 (Long Talk) [arXiv] [slides]
Bandit Multiclass Linear Classification: Efficient Algorithms for the Separable Case
(α-β) Alina Beygelzimer, David Pal, Balazs Szorenyi, Devanathan Thiruvenkatachari, Chen-Yu Wei, Chicheng Zhang
ICML 2019 [arXiv] [code] [slides]

2018

Efficient Online Portfolio with Logarithmic Regret
(α-β) Haipeng Luo, Chen-Yu Wei, Kai Zheng
NeurIPS 2018 (Spotlight) [arXiv] [slides]
Efficient Contextual Bandits in Non-Stationary Worlds
Haipeng Luo*, Chen-Yu Wei*, Alekh Agarwal, John Langford
COLT 2018 [arXiv] [slides] [video]
More Adaptive Algorithms for Adversarial Bandits
Chen-Yu Wei and Haipeng Luo
COLT 2018 [arXiv] [slides] [video]
Multi-Cell Cooperative Scheduling for Network Utility Maximization with User Equipment Side Interference Cancellation
Chen-Yu Wei and Wanjiun Liao
IEEE Transactions on Wireless Communications 2018 [IEEE Xplore]

Before 2018

Online Reinforcement Learning in Stochastic Games
Chen-Yu Wei, Yi-Te Hong, Chi-Jen Lu
NeurIPS 2017 [arXiv]
Tracking the Best Expert in Non-Stationary Stochastic Environments
Chen-Yu Wei, Yi-Te Hong, Chi-Jen Lu
NeurIPS 2016 [arXiv]
Adaptive Measurement for Energy Efficient Mobility Management in Ultra-Dense Small Cell Networks
Hsu Kao, Chen-Yu Wei, Hsiao-Ching Lin, Yi-Han Chiang, Wanjiun Liao
International Conference on Communications 2016 [IEEE Xplore]