Wasserstein-2 Generative Networks

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

ICLR 2021poster130 citations

Wasserstein-2 Generative Networks

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

Abstract

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.

wasserstein-2 distanceoptimal transport mapsnon-minimax optimizationcycle-consistency regularizationinput-convex neural networks

BibTeX

@inproceedings{
korotin2021wasserstein,
title={Wasserstein-2 Generative Networks},
author={Alexander Korotin and Vage Egiazarian and Arip Asadulaev and Alexander Safin and Evgeny Burnaev},
booktitle={International Conference on Learning Representations},
year={2021},
url={https://openreview.net/forum?id=bEoxzW_EXsa}
}