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
Peter L. Chen, Xiaopeng Li, Ziniu Li, Xi Chen, Tianyi Lin, Spectral Policy Optimization: Coloring your Incorrect Reasoning in GRPO.
Preprint on ArXiv: 2505.11595.Théodore Fougereux, Cédric Josz, Xiaopeng Li, Global convergence of gradient descent for phase retrieval.
Preprint on ArXiv: 2410.09990.Cédric Josz, Lexiao Lai, Xiaopeng Li, Proximal random reshuffling under local Lipschitz continuity.
Major revision in Mathematics of Operations Research. Preprint on ArXiv: 2408.07182.
Cédric Josz, Xiaopeng Li. (2024). Singular perturbation in heavy ball dynamics.
Journal of Dynamics and Differential Equations. Preprint on ArXiv: 2407.15044.Cédric Josz, Lexiao Lai, Xiaopeng Li. (2023). Convergence of the momentum method for semi-algebraic functions with locally Lipschitz gradients.
SIAM Journal on Optimization, 33(4), 3012–3037. Preprint on ArXiv: 2307.03331.Cédric Josz, Xiaopeng Li. (2023). Certifying the absence of spurious local minima at infinity.
SIAM Journal on Optimization, 33(3), 1416–1439. Preprint on ArXiv: 2303.03536.