Weiqiang Zheng

Ph.D. Student

Department of Computer Science

Yale University

I am a fifth-year PhD student in Computer Science at Yale University, where I am fortunate to be advised by Prof. Yang Cai. I received my bachelor’s degree in EECS at Peking University, where I was fortunate to be advised by Prof. Xiaotie Deng. During my undergraduate study, I also worked closely with Prof. Lirong Xia.

I have a broad interest in learning, optimization, and economics. My current research focuses on the interdisciplinary area of learning in games, which aims to (1) understand dynamics of strategically learning agents in games; (2) design and analyze fast algrothms for game solving; (3) propose new game-theoretical approaches for practical problems including LLM alignment.

I am honored to be recognized as a KAUST rising star in AI.

Interests

Algorithmic Game theory
Online Learning
Min-Max Optimization

Education

BSc (Summa Cum Laude) in Computer Science, 2021
Peking University

Working Papers

Yang Cai, Gabriele Farian, Julien Grand-Clément, Christian Kroer, Chung-Wei Lee, Haipeng Luo, Weiqiang Zheng (2025). On Separation Between Best-Iterate, Random-Iterate, and Last-Iterate Convergence of Learning in Games. Working Paper.

Cite arXiv

Yixin Liu, Argyris Oikonomou, Weiqiang Zheng, Yang Cai, Arman Cohan (2024). COMAL: A Convergent Meta Algorithm for Aligning LLMs with General Preferences. NeurIPS workshop on Fine-Tuning in Modern Machine Learning: Principles and Scalability (FITML). Selected for Oral Presentation.

arXiv FITML workshop

Publications

Yang Cai, Haipeng Luo, Chen-Yu Wei, Weiqiang Zheng (2025). From Average-Iterate to Last-Iterate Convergence in Games: A Reduction and Its Applications. The 39th Annual Conference on Neural Information Processing Systems (NeurIPS).

Cite arXiv

Yang Cai, Gabriele Farian, Julien Grand-Clément, Christian Kroer, Chung-Wei Lee, Haipeng Luo, Weiqiang Zheng (2025). Last-Iterate Convergence Properties of Regret-Matching Algorithms in Games. The 13th International Conference on Learning Representations (ICLR).

Cite arXiv Openreview

Yang Cai, Constantinos Daskalakis, Haipeng Luo, Chen-Yu Wei, Weiqiang Zheng (2024). On Tractable $\Phi$-Equilibria in Non-Concave Games. The 38th Annual Conference on Neural Information Processing Systems (NeurIPS).

PDF Cite arXiv slides

Yang Cai, Gabriele Farian, Julien Grand-Clément, Christian Kroer, Chung-Wei Lee, Haipeng Luo, Weiqiang Zheng (2024). Fast Last-Iterate Convergence of Learning in Games Requires Forgetful Algorithms. The 38th Annual Conference on Neural Information Processing Systems (NeurIPS).

PDF Cite arXiv

Yang Cai, Argyris Oikonomou, Weiqiang Zheng (2024). Accelerated Algorithms for Constrained Nonconvex-Nonconcave Min-Max Optimization and Comonotone Inclusion. The Forty-first International Conference on Machine Learning (ICML).

PDF Cite arXiv

Yang Cai, Haipeng Luo, Chen-Yu Wei, Weiqiang Zheng (2024). Near-Optimal Policy Optimization for Correlated Equilibrium in General-Sum Markov Games. The 27th International Conference on Artificial Intelligence and Statistics (AISTATS). Selected for Oral Presentation.

PDF Cite arXiv

(*) Jiahao Zhang, Tao Lin, Weiqiang Zheng, Zhe Feng, Yifeng Teng, Xiaotie Deng (2024). Learning Thresholds with Latent Values and Censored Feedback. The Twelfth International Conference on Learning Representations (ICLR).

PDF Cite arXiv Openreview

Yang Cai, Haipeng Luo, Chen-Yu Wei, Weiqiang Zheng (2023). Uncoupled and Convergent Learning in Two-Player Zero-Sum Markov Games with Bandit Feedback. The 37th Annual Conference on Neural Information Processing Systems (NeurIPS).

PDF Cite arXiv

Yang Cai, Weiqiang Zheng (2023). Doubly Optimal No-Regret Learning in Monotone Games. Proceedings of the 40th International Conference on Machine Learning (ICML).

PDF Cite arXiv PMLR

Yang Cai, Weiqiang Zheng (2023). Accelerated Single-Call Methods for Constrained Min-Max Optimization. Proceedings of the 11th International Conference on Learning Representations (ICLR).

PDF Cite arXiv Openreview

Lirong Xia, Weiqiang Zheng (2022). Beyond the Worst Case: Semi-random Complexity Analysis of Winner Determination. The 18th Conference on Web and Internet Economics (WINE).

PDF Cite arXiv DOI

Yang Cai, Argyris Oikonomou, Weiqiang Zheng (2022). Finite-Time Last-Iterate Convergence for Learning in Multi-Player Games. The 36th Annual Conference on Neural Information Processing Systems (NeurIPS). Selected for Oral Presentation.

PDF Cite video openreivew

Yang Cai, Argyris Oikonomou, Weiqiang Zheng (2022). Tight Last-Iterate Convergence of the Extragradient and the Optimistic Gradient Descent-Ascent Algorithm for Constrained Monotone Variational Inequalities. Preliminary Version of the NeurIPS 2022 Paper Above.

PDF Cite arXiv

Xiaotie Deng, Xinyan Hu, Tao Lin, Weiqiang Zheng (2022). Nash Convergence of Mean-Based Learning Algorithms in First Price Auctions. Proceedings of the ACM Web Conference (WWW).

PDF Cite DOI arXiv video doi

Dezhi Ran, Weiqiang Zheng, Yunqi Li, Kaigui Bian, Jie Zhang, Xiaotie Deng (2022). Revenue and User Traffic Maximization in Mobile Short-Video Advertising. Proceedings of the 21st International Conference on Autonomous Agents and Multiagent Systems (AAMAS).

PDF Cite doi

Lirong Xia, Weiqiang Zheng (2021). The Smoothed Complexity of Computing Kemeny and Slater Rankings. Proceedings of the AAAI Conference on Artificial Intelligence (AAAI).

PDF Cite arXiv video