Neural Monge Map estimation and its applications

Monge map refers to the optimal transport map between two probability distributions and provides a principled approach to transform one distribution to another. Neural network based optimal transport map solver has gained great attention in recent years. Along this line, we present a scalable algori...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Fan, Jiaojiao, Liu, Shu, Ma, Shaojun, Zhou, Haomin, Chen, Yongxin
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 19.11.2022
Subjects
Algorithms
Computation
Cost function
Numerical methods
Online AccessGet full text

Cover

More Information
Summary:Monge map refers to the optimal transport map between two probability distributions and provides a principled approach to transform one distribution to another. Neural network based optimal transport map solver has gained great attention in recent years. Along this line, we present a scalable algorithm for computing the neural Monge map between two probability distributions. Our algorithm is based on a weak form of the optimal transport problem, thus it only requires samples from the marginals instead of their analytic expressions, and can accommodate optimal transport between two distributions with different dimensions. Our algorithm is suitable for general cost functions, compared with other existing methods for estimating Monge maps using samples, which are usually for quadratic costs. The performance of our algorithms is demonstrated through a series of experiments with both synthetic and realistic data, including text-to-image generation and image inpainting tasks.
ISSN:2331-8422