Kernel Neural Optimal Transport

Alexander Korotin; Daniil Selikhanovych; Evgeny Burnaev

ICLR 2023poster24 citations

Kernel Neural Optimal Transport

Alexander Korotin, Daniil Selikhanovych, Evgeny Burnaev

Abstract

We study the Neural Optimal Transport (NOT) algorithm which uses the general optimal transport formulation and learns stochastic transport plans. We show that NOT with the weak quadratic cost may learn fake plans which are not optimal. To resolve this issue, we introduce kernel weak quadratic costs. We show that they provide improved theoretical guarantees and practical performance. We test NOT with kernel costs on the unpaired image-to-image translation task.

optimal transportneural networkskernels

BibTeX

@inproceedings{
korotin2023kernel,
title={Kernel Neural Optimal Transport},
author={Alexander Korotin and Daniil Selikhanovych and Evgeny Burnaev},
booktitle={The Eleventh International Conference on Learning Representations },
year={2023},
url={https://openreview.net/forum?id=Zuc_MHtUma4}
}