Mengxiao Zhang 张梦晓

alt text 

Ph.D student,
Computer Science Department,
University of Southern California
Email: zhan147 at usc dot edu
Google Scholar

About me

I am currently a fifth year Ph.D student in computer science from University of Southern California. I am very fortunate to be advised by Prof. Haipeng Luo. I complete my bachelor degree at Peking University and am fortunate to be advised by Prof. Liwei Wang.

My general research interests lie in designing practical and adaptive machine learning algorithms with strong theoretical guarantees.

Research

My research interests include

  • Online learning and bandits

  • Reinforcement learning

  • Game Theory

Teaching Assistant

  • CSCI 570: Analysis of Algorithms, Instructor: Victor Adamchik, Spring 2020

  • CSCI 567: Machine Learning, Instructor: Haipeng Luo, Fall 2020

  • CSCI 567: Machine Learning, Instructor: Haipeng Luo, Fall 2021

  • CSCI 670: Advanced Analysis of Algorithms, Instructor: Ming-Deh Huang, Spring 2022

Selected publications (reverse chronological)

  1. [COLT 2022] Corralling a Larger Band of Bandits: A Case Study on Switching Regret for Linear Bandits
    Haipeng Luo*, Mengxiao Zhang*, Peng Zhao*, Zhi-Hua Zhou*.

  2. [COLT 2022] Adaptive Bandit Convex Optimization with Heterogeneous Curvature
    Haipeng Luo*, Mengxiao Zhang*, Peng Zhao*.

  3. [ICML 2022] No-Regret Learning in Time-Varying Zero-Sum Games
    Mengxiao Zhang*, Peng Zhao*, Haipeng Luo, Zhi-Hua Zhou.

  4. [COLT 2021] Last-iterate Convergence of Decentralized Optimistic Gradient Descent/Ascent in Infinite-horizon Competitive Markov Games.
    Chen-Yu Wei, Chung-Wei Lee*, Mengxiao Zhang*, and Haipeng Luo.

  5. [ICML 2021] Achieving Near Instance-Optimality and Minimax-Optimality in Stochastic and Adversarial Linear Bandits Simultaneously.
    Chung-Wei Lee*, Haipeng Luo*, Chen-Yu Wei*, Mengxiao Zhang*, Xiaojin Zhang*.

  6. [ICLR 2021] Linear Last-iterate Convergence in Constrained Saddle-point Optimization.
    Chen-Yu Wei, Chung-Wei Lee, Mengxiao Zhang, and Haipeng Luo.

  7. [NeurIPS 2020 Oral] Bias no more: high-probability data-dependent regret bounds for adversarial bandits and MDPs.
    Chung-Wei Lee*, Haipeng Luo*, Chen-Yu Wei*, and Mengxiao Zhang*.

  8. [COLT 2020] A Closer Look at Small-loss Bounds for Bandits with Graph Feedback.
    Chung-Wei Lee*, Haipeng Luo*, and Mengxiao Zhang*.