A Generalized Sinkhorn Algorithm for Mean-Field Schrödinger Bridge

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Eldesoukey, Asmaa, Chen, Yongxin, Halder, Abhishek
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908949706440704
author Eldesoukey, Asmaa
Chen, Yongxin
Halder, Abhishek
author_facet Eldesoukey, Asmaa
Chen, Yongxin
Halder, Abhishek
contents The mean-field Schrödinger bridge (MFSB) problem concerns designing a minimum-effort controller that guides a diffusion process with nonlocal interaction to reach a given distribution from another by a fixed deadline. Unlike the standard Schrödinger bridge, the dynamical constraint for MFSB is the mean-field limit of a population of interacting agents with controls. It serves as a natural model for large-scale multi-agent systems. The MFSB is computationally challenging because the nonlocal interaction makes the problem nonconvex. We propose a generalization of the Hopf-Cole transform for MFSB and, building on it, design a Sinkhorn-type recursive algorithm to solve the associated system of integro-PDEs. Under mild assumptions on the interaction potential, we discuss convergence guarantees for the proposed algorithm. We present numerical examples with repulsive and attractive interactions to illustrate the theoretical contributions.
format Preprint
id arxiv_https___arxiv_org_abs_2604_06531
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle A Generalized Sinkhorn Algorithm for Mean-Field Schrödinger Bridge
Eldesoukey, Asmaa
Chen, Yongxin
Halder, Abhishek
Optimization and Control
Machine Learning
Multiagent Systems
Systems and Control
The mean-field Schrödinger bridge (MFSB) problem concerns designing a minimum-effort controller that guides a diffusion process with nonlocal interaction to reach a given distribution from another by a fixed deadline. Unlike the standard Schrödinger bridge, the dynamical constraint for MFSB is the mean-field limit of a population of interacting agents with controls. It serves as a natural model for large-scale multi-agent systems. The MFSB is computationally challenging because the nonlocal interaction makes the problem nonconvex. We propose a generalization of the Hopf-Cole transform for MFSB and, building on it, design a Sinkhorn-type recursive algorithm to solve the associated system of integro-PDEs. Under mild assumptions on the interaction potential, we discuss convergence guarantees for the proposed algorithm. We present numerical examples with repulsive and attractive interactions to illustrate the theoretical contributions.
title A Generalized Sinkhorn Algorithm for Mean-Field Schrödinger Bridge
topic Optimization and Control
Machine Learning
Multiagent Systems
Systems and Control
url https://arxiv.org/abs/2604.06531