学术报告报告题目: Min-Max Optimization for Training Generative Adversarial Networks
报 告 人: Xiaojun Chen 教授
报告时间: 2026年 3月 6 日（星期五）10:00-12:00
地 点：37号楼3A02
邀 请 人: 潘少华教授
欢迎广大师生前往！
数学学院
2026年3月2日
报告摘要：
This talk considers nonsmooth nonconvex-nonconcave min-max optimization problems with applications from robust nonlinear least square problems and training generative adversarial networks. We discuss the existence of local saddle points, global minimax points and local minimax points, and study the optimality conditions for local minimax points. We give an explicit formula for the value function of the inner maximization problem of a class of robust nonlinear least square problems and complexity bound for finding an approximate first order stationary point. A smoothing quasi-Newton subspace trust region algorithm is presented for training generative adversarial networks as nonsmooth nonconvex-nonconcave min-max optimization problems. Examples of retinal vessel segmentation in fundoscopic images are used to illustrate the efficiency of the algorithm.
报告人简介：
Xiaojun Chen is a Chair Professor of Department of Applied Mathematics, Hong Kong Polytechnic University. She is the Co-Director of CAS AMSS-PolyU Joint Laboratory of Applied Mathematics. Her research interests focus on mathematical optimization theory and algorithms for nonsmooth nonconvex optimization problems and stochastic variational inequalities with applications in data sciences. She is the PI of several large grants from Hong Kong Research Grant Council and Croucher Foundation. She published over 100 papers in top journals in applied mathematics. She is an Area Editor of Journal of Optimization Theory and Applications. She served/serves SIAM Journal on Numerical Analysis, SIAM Journal on Optimization and SIAM Journal on Control and Optimization as an Associate Editor. She is a fellow of Society for Industrial and Applied Mathematics (SIAM) and a fellow of American Mathematical Society (AMS). She is a Keynote speaker of the 25th International Symposium on Mathematical Programming in Canada 2024 and the 16th Viennese Conference on Optimal Control and Dynamic Games in Austria 2025, and an invited 45-minute speaker in the International Congress of Mathematics (ICM) in Philadelphia 2026.