On the Gradient Formula for learning Generative Models with Regularized Optimal Transport Costs

The use of optimal transport costs for learning generative models has become popular with Wasserstein Generative Adversarial Networks (WGANs). Training a WGAN requires the computation of the differentiation of the optimal transport cost with respect to the parameters of the generative model. In this...

Full description

Saved in:
Bibliographic Details
Published inTransactions on Machine Learning Research Journal
Main Authors Houdard, Antoine, Leclaire, Arthur, Papadakis, Nicolas, Rabin, Julien
Format Journal Article
LanguageEnglish
Published [Amherst Massachusetts]: OpenReview.net, 2022 14.07.2023
Subjects
Online AccessGet full text

Cover

Loading…