A Generalized Sinkhorn Algorithm for Mean-Field Schrödinger Bridge
IEEE Control Systems Letters · 2026 · 10 · 1087-1092
DOI: 10.1109/lcsys.2026.3704530 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Control Systems Letters, 2026. Verfasst von Asmaa Eldesoukey und 2 weiteren Autor:innen. Die Arbeit nennt 30 Literaturangaben. Gefördert von: NSF.
Abstract (Originalsprache)
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. We analyze the local convergence of the proposed algorithm. We also present numerical examples with repulsive and attractive interactions to illustrate the theoretical contributions.
Förderung
- NSF
Zitieren
APA
Eldesoukey, A., Chen, Y., & Halder, A. (2026). A Generalized Sinkhorn Algorithm for Mean-Field Schrödinger Bridge. IEEE Control Systems Letters, 10, 1087-1092. https://doi.org/10.1109/lcsys.2026.3704530
Vancouver
Eldesoukey A, Chen Y, Halder A. A Generalized Sinkhorn Algorithm for Mean-Field Schrödinger Bridge. IEEE Control Systems Letters. 2026;10:1087-1092. doi:10.1109/lcsys.2026.3704530
BibTeX
@article{Eldesoukey2026,
author = {Eldesoukey, Asmaa and Chen, Yongxin and Halder, Abhishek},
title = {A Generalized Sinkhorn Algorithm for Mean-Field Schrödinger Bridge},
journal = {IEEE Control Systems Letters},
year = {2026},
volume = {10},
pages = {1087--1092},
doi = {10.1109/lcsys.2026.3704530}
}
EUVIMED