Saved in:
Bibliographic Details
Main Authors: Jiang, Mingchen, Xu, Peng, Ye, Xichen, Chen, Xiaohui, Yang, Yun, Chen, Yifan
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2504.17740
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913806987296768
author Jiang, Mingchen
Xu, Peng
Ye, Xichen
Chen, Xiaohui
Yang, Yun
Chen, Yifan
author_facet Jiang, Mingchen
Xu, Peng
Ye, Xichen
Chen, Xiaohui
Yang, Yun
Chen, Yifan
contents Distributional data have become increasingly prominent in modern signal processing, highlighting the necessity of computing optimal transport (OT) maps across multiple probability distributions. Nevertheless, recent studies on neural OT methods predominantly focused on the efficient computation of a single map between two distributions. To address this challenge, we introduce a novel approach to learning transport maps for new empirical distributions. Specifically, we employ the transformer architecture to produce embeddings from distributional data of varying length; these embeddings are then fed into a hypernetwork to generate neural OT maps. Various numerical experiments were conducted to validate the embeddings and the generated OT maps. The model implementation and the code are provided on https://github.com/jiangmingchen/HOTET.
format Preprint
id arxiv_https___arxiv_org_abs_2504_17740
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Embedding Empirical Distributions for Computing Optimal Transport Maps
Jiang, Mingchen
Xu, Peng
Ye, Xichen
Chen, Xiaohui
Yang, Yun
Chen, Yifan
Machine Learning
Distributional data have become increasingly prominent in modern signal processing, highlighting the necessity of computing optimal transport (OT) maps across multiple probability distributions. Nevertheless, recent studies on neural OT methods predominantly focused on the efficient computation of a single map between two distributions. To address this challenge, we introduce a novel approach to learning transport maps for new empirical distributions. Specifically, we employ the transformer architecture to produce embeddings from distributional data of varying length; these embeddings are then fed into a hypernetwork to generate neural OT maps. Various numerical experiments were conducted to validate the embeddings and the generated OT maps. The model implementation and the code are provided on https://github.com/jiangmingchen/HOTET.
title Embedding Empirical Distributions for Computing Optimal Transport Maps
topic Machine Learning
url https://arxiv.org/abs/2504.17740