Jintao Xu

Postdoc, Hong Kong Polytechnic University

1 paper at NeurIPS 2025

Homepage· OpenReview· Semantic Scholar· Google Scholar

Poster Session 3

1 paper

Thursday, December 4, 2025 · 11:00 AM → 2:00 PM

Exhibit Hall C,D,E

A Regularized Newton Method for Nonconvex Optimization with Global and Local Complexity Guarantees

#1000 · Yuhao Zhou, Jintao Xu, Bingrui Li, Chenglong Bao, Chao Ding, Jun Zhu

A parameter-free regularized Newton-type algorithm that simultaneously achieves optimal global complexity and quadratic local convergence in nonconvex optimization.