Skip to yearly menu bar Skip to main content


Wasserstein-2 Generative Networks

Alexander Korotin · Vage Egiazarian · Arip Asadulaev · Alexander Safin · Evgeny Burnaev


Keywords: [ input-convex neural networks ] [ cycle-consistency regularization ] [ non-minimax optimization ] [ optimal transport maps ] [ wasserstein-2 distance ]


We propose a novel end-to-end non-minimax algorithm for training optimal transport mappings for the quadratic cost (Wasserstein-2 distance). The algorithm uses input convex neural networks and a cycle-consistency regularization to approximate Wasserstein-2 distance. In contrast to popular entropic and quadratic regularizers, cycle-consistency does not introduce bias and scales well to high dimensions. From the theoretical side, we estimate the properties of the generative mapping fitted by our algorithm. From the practical side, we evaluate our algorithm on a wide range of tasks: image-to-image color transfer, latent space optimal transport, image-to-image style transfer, and domain adaptation.

Chat is not available.