Chung-Wei Lee
[Google Scholar]
[email protected]
I am a researcher at WorldQuant, where my research interest is applying machine learning and artificial intelligence to quantitative finance. I hold a PhD in Computer Science at the University of Southern California, where I was very fortunate to be advised by Prof. Haipeng Luo. My PhD research centers around the intersection of theoretical machine learning and algorithmic game theory. Specifically, I study fundamental sequential decision-making problems involving multiple agents in partially observable environments. Prior to pursuing my PhD, I received my B.S. from National Taiwan University, double majoring in Electrical Engineering and Mathematics. During that time, I had the privilege of working alongside Prof. Yu-Chiang Frank Wang on Computer Vision and Deep Learning projects.
Work Experience
Publications
Context-lumpable Stochastic Bandits
Chung-Wei Lee, Qinghua Liu, Yasin Abbasi-Yadkori, Chi Jin, Tor Lattimore, Csaba SzepesváriConference on Neural Information Processing Systems (NeurIPS) 2023.
[arxiv]
Regret Matching+: (In)Stability and Fast Convergence in Games
(α-β order) Gabriele Farina, Julien Grand-Clément, Christian Kroer, Chung-Wei Lee, Haipeng LuoConference on Neural Information Processing Systems (NeurIPS) 2023. (Spotlight)
[arxiv]
Uncoupled Learning Dynamics with O(log T) Swap Regret in Multiplayer Games
(α-β order) Ioannis Anagnostides, Gabriele Farina, Christian Kroer, Chung-Wei Lee, Haipeng Luo, Tuomas SandholmConference on Neural Information Processing Systems (NeurIPS) 2022. (Oral)
[arxiv]
Near-Optimal No-Regret Learning Dynamics for General Convex Games
Gabriele Farina, Ioannis Anagnostides, Haipeng Luo, Chung-Wei Lee, Christian Kroer, Tuomas SandholmConference on Neural Information Processing Systems (NeurIPS) 2022.
[arxiv]
Kernelized Multiplicative Weights for 0/1-Polyhedral Games: Bridging the Gap Between Learning in Extensive-Form and Normal-Form Games
Gabriele Farina, Chung-Wei Lee, Haipeng Luo, Christian KroerInternational Conference on Machine Learning (ICML) 2022.
[arxiv]
Last-iterate Convergence in Extensive-form Games
Chung-Wei Lee, Christian Kroer, Haipeng LuoConference on Neural Information Processing Systems (NeurIPS) 2021.
[arxiv]
Policy Optimization in Adversarial MDPs: Improved Exploration via Dilated Bonuses
Haipeng Luo, Chen-Yu Wei, Chung-Wei LeeConference on Neural Information Processing Systems (NeurIPS) 2021.
[arxiv]
Achieving Near Instance-Optimality and Minimax-Optimality in Stochastic and Adversarial Linear Bandits Simultaneously
(α-β order) Chung-Wei Lee, Haipeng Luo, Chen-Yu Wei, Mengxiao Zhang, Xiaojin ZhangInternational Conference on Machine Learning (ICML) 2021.
[arxiv]
Last-iterate Convergence of Decentralized Optimistic Gradient Descent/Ascent in Infinite-horizon Competitive Markov Games
Chen-Yu Wei, Chung-Wei Lee, Mengxiao Zhang, Haipeng LuoAnnual Conference on Learning Theory (COLT) 2021.
[arxiv]
Linear Last-iterate Convergence in Constrained Saddle-point Optimization
Chen-Yu Wei, Chung-Wei Lee, Mengxiao Zhang, Haipeng LuoConference on Learning Representations (ICLR) 2021.
[arxiv]
Bias No More: High-probability Data-dependent Regret Bounds for Adversarial Bandits and MDPs
(α-β order) Chung-Wei Lee, Haipeng Luo, Chen-Yu Wei, Mengxiao ZhangConference on Neural Information Processing Systems (NeurIPS) 2020. (Oral)
[arxiv]
A Closer Look at Small-loss Bounds for Bandits with Graph Feedback
(α-β order) Chung-Wei Lee, Haipeng Luo, Mengxiao ZhangAnnual Conference on Learning Theory (COLT) 2020.
[arxiv]
A New Algorithm for Non-stationary Contextual Bandits: Efficient, Optimal, and Parameter-free
(α-β order) Yifang Chen, Chung-Wei Lee, Haipeng Luo, Chen-Yu WeiAnnual Conference on Learning Theory (COLT) 2019.
[arxiv]
Multi-Label Zero-Shot Learning with Structured Knowledge Graphs
Chung-Wei Lee, Wei Fang, Chih-Kuan Yeh, Yu-Chiang Frank WangIEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2018.
[arxiv]
Preprints
Practical Knowledge Distillation: Using DNNs to Beat DNNs
Chung-Wei Lee, Pavlos Athanasios Apostolopulos, Igor L. MarkovIntern project report.
[arxiv]