Xiaopeng Li
 |
Xiaopeng Li |
Research
Ph.D. Advisor: Professor Cédric Josz
My research interest lies in nonconvex optimization, differential equations, semi-algebraic geometry, with applications in low rank matrix recovery, deep neural networks, and large language model reasoning.
Openings
I am actively recruiting PhD students who are interested in optimization for machine learning, nonconvex/nonsmooth optimization, or LLM reasoning. Strong mathematical background and solid programming skills are important; prior research experience is a plus.
Publications
Singular perturbation in heavy ball dynamics, with Cédric Josz
Journal of Dynamics and Differential Equations, 2024. Preprint on ArXiv: 2407.15044.Convergence of the momentum method for semi-algebraic functions with locally Lipschitz gradients, with Cédric Josz and Lexiao Lai
SIAM Journal on Optimization, 2023. Preprint on ArXiv: 2307.03331.Certifying the absence of spurious local minima at infinity, with Cédric Josz
SIAM Journal on Optimization, 2023. Preprint on ArXiv: 2303.03536.
Exploration vs exploitation: Rethinking rlvr through clipping, entropy, and spurious reward, with Peter L. Chen, Ziniu Li, Wotao Yin, Xi Chen and Tianyi Lin
Proceedings of the International Conference on Learning Representations (ICLR), 2026. Preprint on ArXiv: 2512.16912.
Reward-free Alignment for Conflicting Objectives, with Peter L. Chen, Xi Chen and Tianyi Lin, 2026
Preprint on ArXiv: 2602.02495.Spectral Policy Optimization: Coloring your Incorrect Reasoning in GRPO, with Peter L. Chen, Ziniu Li, Xi Chen and Tianyi Lin, 2025
Preprint on ArXiv: 2505.11595.Global convergence of gradient descent for phase retrieval, with Théodore Fougereux and Cédric Josz, 2024
Preprint on ArXiv: 2410.09990.Proximal random reshuffling under local Lipschitz continuity, with Cédric Josz and Lexiao Lai
Major revision in Mathematics of Operations Research, 2024. Preprint on ArXiv: 2408.07182.