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

Professor Xiao Li is an Assistant Professor at the School of Data Science (SDS) at The Chinese University of Hong Kong, Shenzhen. He earned his Ph.D. degree from The Chinese University of Hong Kong in 2020 and his B.Eng. degree from Zhejiang University of Technology in 2016. From October 2018 to April 2019, he was a visiting scholar at the University of Southern California.

Professor Li’s research focuses on stochastic, nonsmooth, nonconvex optimization, and large language models. His contributions have been recognized with several honors, including the Presidential Young Fellow Award and the SDS Young Faculty Outstanding Teaching Award. He has also served as an Area Chair for CPAL 2024 and CPAL 2025.

1. Xiliang Yang, Feng Jiang, Qianen Zhang, Lei Zhao, Xiao Li (2025). DPO-Shift: Shifting the Distribution of Direct Preference Optimization. arXiv preprint arXiv:2502.07599. 

2. Qijun Luo, Hengxu Yu, Xiao Li (2024). BAdam: A Memory Efficient Full Parameter Optimization Method for Large Language Models. Advances in Neural Information Processing Systems (NeurIPS). 

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

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

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

6. 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. 

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