Wasserstein Proximal of GANs
From MaRDI portal
Publication:6360508
Abstract: 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.
This page was built for publication: Wasserstein Proximal of GANs
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6360508)
