School of Mathematical Sciences, Shenzhen University
Xiaoyin Hu
Associate Professor, School of Mathematical Sciences, Shenzhen University
I work on nonsmooth optimization, Riemannian optimization, and optimization problems in machine learning.
Selected Publications
View allDeveloping Lagrangian-based methods for nonsmooth nonconvex optimization
Nachuan Xiao, Kuangyu Ding, Xiaoyin Hu, Kim-Chuan Toh. Mathematics of Operations Research, 2026.
A minimization approach for minimax optimization with coupled constraints
Xiaoyin Hu, Kim-Chuan Toh, Shiwei Wang, Nachuan Xiao. SIAM Journal on Optimization, 2026.
Adam-family Methods for Nonsmooth Optimization with Convergence Guarantees
Nachuan Xiao, Xiaoyin Hu, Xin Liu, Kim-Chuan Toh. Journal of Machine Learning Research, 2024.
A constraint dissolving approach for nonsmooth optimization over the stiefel manifold
Xiaoyin Hu, Nachuan Xiao*, Xin Liu, Kim-Chuan Toh. IMA Journal of Numerical Analysis, Volume 44, Issue 6, November 2024, Pages 3717-3748.
An improved unconstrained approach for bilevel optimization
Xiaoyin Hu, Nachuan Xiao*, Xin Liu, Kim-Chuan Toh. SIAM Journal on Optimization, 2023, 33(4): 2801-2829.
Software
Current Grant
深度学习中的流形优化问题:算法设计与求解软件包的开发
国家自然科学基金委员会,青年基金,主持. 2024.01-2026.12
View all grantsCurrent Position
Shenzhen University
School of Mathematical Sciences, 2025.10-present
