Xiang Li

prof_pic.jpg

By Weiming Lake

Peking University

I am currently a post-doctoral researcher at University of Pennsylvania, working with Prof. Qi Long and Prof. Weijie Su.

I obtained my Ph.D. degree at School of Mathematical Sciences, Peking University in 2023, advised by Prof. Zhihua Zhang.

My research interests center around the intersection of statistics, stochastic optimization, and machine learning.

During my Ph.D., I conducted research in areas such as federated learning, stochastic approximation, online decision making, and online statistical inference.

More recently, I have shifted my focus to large language models.

news

Dec 9, 2023 Attend NeurIPS 2023.
Sep 26, 2023 Attend Allerton Conf.
Aug 12, 2023 Start postdoc in Upenn.
Jul 4, 2023 Graduate from Peking University. Finish my nine-year study therein.
Feb 11, 2023 Finish my visit at UoT.

selected publications

  1. ICLROral presentaton
    On the convergence of FedAvg on non-iid data
    Xiang Li*, Kaixuan Huang*, Wenhao Yang*, Shusen Wang, and Zhihua Zhang
    In International Conference on Learning Representations, 2020
    HTML Code Poster Slides
  2. COLT
    Statistical estimation and online inference via Local SGD
    Xiang Li, Jiadong Liang, Xiangyu Chang, and Zhihua Zhang
    In Conference on Learning Theory, 2022
    HTML Slides
  3. NeurIPSSpotlight
    Asymptotic behaviors of projected stochastic approximation: A jump diffusion perspective
    Jiadong Liang, Yuze Han, Xiang Li, and Zhihua Zhang
    In Advances in Neural Information Processing Systems, 2022
    HTML Slides
  4. AISTATS
    A statistical analysis of Polyak-Ruppert averaged Q-learning
    Xiang Li, Wenhao Yang, Jiadong Liang, Zhihua Zhang, and Michael I Jordan
    In International Conference on Artificial Intelligence and Statistics, 2023
    arXiv Code Poster Slides Video
  5. Submitted
    Online statistical inference for nonlinear stochastic approximation with Markovian data
    Xiang Li, Jiadong Liang, and Zhihua Zhang
    arXiv preprint arXiv:2302.07690, 2023
    arXiv
  6. Submitted
    Variance-aware robust reinforcement learning with linear function approximation with heavy-tailed rewards
    Xiang Li, and Qiang Sun
    arXiv preprint arXiv:2303.05606, 2023
    arXiv