English

Adversarial Computation of Optimal Transport Maps

Machine Learning 2019-06-25 v1 Machine Learning

Abstract

Computing optimal transport maps between high-dimensional and continuous distributions is a challenging problem in optimal transport (OT). Generative adversarial networks (GANs) are powerful generative models which have been successfully applied to learn maps across high-dimensional domains. However, little is known about the nature of the map learned with a GAN objective. To address this problem, we propose a generative adversarial model in which the discriminator's objective is the 22-Wasserstein metric. We show that during training, our generator follows the W2W_2-geodesic between the initial and the target distributions. As a consequence, it reproduces an optimal map at the end of training. We validate our approach empirically in both low-dimensional and high-dimensional continuous settings, and show that it outperforms prior methods on image data.

Keywords

Cite

@article{arxiv.1906.09691,
  title  = {Adversarial Computation of Optimal Transport Maps},
  author = {Jacob Leygonie and Jennifer She and Amjad Almahairi and Sai Rajeswar and Aaron Courville},
  journal= {arXiv preprint arXiv:1906.09691},
  year   = {2019}
}
R2 v1 2026-06-23T10:01:20.736Z