LI, Xiao

Assistant Professor

Education Background

Ph.D. in Electronic Engineering, The Chinese University of Hong Kong, 2020
B.Eng. in Communication Engineering, Zhejiang University of Technology, 2016

Research Field
Continuous Optimizatin (Nonsmooth, Nonconvex, Stochastic), and with Applications to Machine Learning and Signal Processing
Personal Website
Room 506a, Daoyuan Building

Professor Xiao Li  is an Assistant Professor at the School of Data Science, the Chinese University of Hong Kong, Shenzhen. Professor Li received his B.Eng. degree from Zhejiang University of Technology in 2016, and obtained his Ph.D. degree from the Chinese University of Hong Kong in 2020. Professor Li went to the University of Southern California as the Visiting Scholar from October 2018 to April 2019.

Professor Li’s research interests include data science, computational imaging, machine learning, and mathematical optimization. He has participated in many international conferences and workshops, and his works have been published in many conference proceedings including NeurIPS, ICLR, etc. What’s more, Prof Li has published his research on many world-leading journals, such as SIAM Journal on Optimization, SIAM Journal on Imaging Science, IEEE Transactions on Image Processing and so on.

Academic Publications

1. Qijun Luo, Xiao Li (2023). Finite-Time Analysis of Decentralized Single-Timescale Actor-Critic. Transactions on Machine Learning Research.

2. Xiao Li, Andre Milzarek, Junwen Qiu (2023). Convergence of Random Reshuffling Under The Kurdyka-Lojasiewicz Inequality. SIAM Journal on Optimization.

3. Xiao Li, Andre Milzarek (2022). A Unified Convergence Theorem for Stochastic Optimization Methods. Neural Information Processing Systems (NeurIPS).

4. Xiao Li, Shixiang Chen, Zengde Deng, Qing Qu, Zhihui Zhu, and Anthony Man-Cho So (2021). Weakly convex optimization over Stiefel manifold using Riemannian subgradient-type methods. SIAM Journal on Optimization.

5. Xiao Li, Zhihui Zhu, Anthony Man-Cho So, Rene Vidal (2020). Nonconvex Robust Low-rank Matrix Recovery. SIAM Journal on Optimization.