BM$^2$: Coupled Schrödinger Bridge Matching

Fuente: arXiv
Saved in:
Bibliographic Details
Main Author: Peluchetti, Stefano
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909459797770240
author Peluchetti, Stefano
author_facet Peluchetti, Stefano
contents A Schrödinger bridge establishes a dynamic transport map between two target distributions via a reference process, simultaneously solving an associated entropic optimal transport problem. We consider the setting where samples from the target distributions are available, and the reference diffusion process admits tractable dynamics. We thus introduce Coupled Bridge Matching (BM$^2$), a simple non-iterative approach for learning Schrödinger bridges with neural networks. A preliminary theoretical analysis of the convergence properties of BM$^2$ is carried out, supported by numerical experiments that demonstrate the effectiveness of our proposal.
format Preprint
id arxiv_https___arxiv_org_abs_2409_09376
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle BM$^2$: Coupled Schrödinger Bridge Matching
Peluchetti, Stefano
Machine Learning
A Schrödinger bridge establishes a dynamic transport map between two target distributions via a reference process, simultaneously solving an associated entropic optimal transport problem. We consider the setting where samples from the target distributions are available, and the reference diffusion process admits tractable dynamics. We thus introduce Coupled Bridge Matching (BM$^2$), a simple non-iterative approach for learning Schrödinger bridges with neural networks. A preliminary theoretical analysis of the convergence properties of BM$^2$ is carried out, supported by numerical experiments that demonstrate the effectiveness of our proposal.
title BM$^2$: Coupled Schrödinger Bridge Matching
topic Machine Learning
url https://arxiv.org/abs/2409.09376