Kernel Neural Optimal Transport
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.
Cite
Text
Korotin et al. "Kernel Neural Optimal Transport." International Conference on Learning Representations, 2023.Markdown
[Korotin et al. "Kernel Neural Optimal Transport." International Conference on Learning Representations, 2023.](https://mlanthology.org/iclr/2023/korotin2023iclr-kernel/)BibTeX
@inproceedings{korotin2023iclr-kernel,
title = {{Kernel Neural Optimal Transport}},
author = {Korotin, Alexander and Selikhanovych, Daniil and Burnaev, Evgeny},
booktitle = {International Conference on Learning Representations},
year = {2023},
url = {https://mlanthology.org/iclr/2023/korotin2023iclr-kernel/}
}