Wasserstein Proximal of GANs
Lin, Alex Tong, Li, Wuchen, Osher, Stanley, Montufar, Guido
–arXiv.org Artificial Intelligence
We introduce a new method for training generative adversarial networks by applying the Wasserstein-2 metric proximal on the generators. The approach is based on Wasserstein information geometry. It defines a parametrization invariant natural gradient by pulling back optimal transport structures from probability space to parameter space. We obtain easy-to-implement iterative regularizers for the parameter updates of implicit deep generative models. Our experiments demonstrate that this method improves the speed and stability of training in terms of wall-clock time and Fr\'echet Inception Distance.
arXiv.org Artificial Intelligence
Feb-13-2021