Title:  Min-Max Optimization for Training Generative Adversarial Networks  

Speaker:   Xiaojun Chen  (Professor)

Time:  Mar 6, 2026,10:00-12:00

Venue: Room 3A02, Building No. 37, Wushan Campus

Abstract: 

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.