SOTAVerified

Neural Optimal Transport

2022-01-28Code Available2· sign in to hype

Alexander Korotin, Daniil Selikhanovych, Evgeny Burnaev

Code Available — Be the first to reproduce this paper.

Reproduce

Code

Abstract

We present a novel neural-networks-based algorithm to compute optimal transport maps and plans for strong and weak transport costs. To justify the usage of neural networks, we prove that they are universal approximators of transport plans between probability distributions. We evaluate the performance of our optimal transport algorithm on toy examples and on the unpaired image-to-image translation.

Tasks

Reproductions