Towards a Better Global Loss Landscape of GANs

               Ruoyu Sun, Tiantian Fang, Alex Schwing
               University of Illinois at Urbana-Champaign
               ruoyus,tf6,aschwing@illinois.edu
                       Abstract
     Understanding of GAN training is still very limited. One major challenge is its
     non-convex-non-concave min-max objective, which may lead to sub-optimal local
     minima. In this work, we perform a global landscape analysis of the empirical
     loss ...