A Regime-Switching Approach to the Unbalanced Schrödinger Bridge Problem

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Zlotchevski, Andrei, Chen, Linan
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909962877272064
author Zlotchevski, Andrei
Chen, Linan
author_facet Zlotchevski, Andrei
Chen, Linan
contents The unbalanced Schrödinger bridge problem (uSBP) seeks to interpolate between a probability measure $ρ_0$ and a sub-probability measure $ρ_T$ while minimizing KL divergence to a reference measure $\mathbf{R}$ on a path space. In this work, we investigate the case where $\mathbf{R}$ is the path measure of a diffusion process with killing, which we interpret as a regime-switching diffusion. In addition to matching the initial and terminal distributions of trajectories that survive up to time $T$, we consider a general constraint $ψ(t,x)$ on the distribution of killing times and/or killing locations. We investigate the uSBPs corresponding to four choices of $ψ$ in detail which reflect different levels of information available to an observer. We also provide a rigorous analysis of the connections and the comparisons among the outcomes of these four cases. Our results are novel in the field of uSBP. The regime-switching approach proposed in this work provides a unified framework for tackling different uSBP scenarios, which not only reconciles but also extends the existing literature on uSBP.
format Preprint
id arxiv_https___arxiv_org_abs_2512_12971
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Regime-Switching Approach to the Unbalanced Schrödinger Bridge Problem
Zlotchevski, Andrei
Chen, Linan
Probability
Optimization and Control
35Q93, 60H10, 60H30, 60J60, 93E20, 94A17
The unbalanced Schrödinger bridge problem (uSBP) seeks to interpolate between a probability measure $ρ_0$ and a sub-probability measure $ρ_T$ while minimizing KL divergence to a reference measure $\mathbf{R}$ on a path space. In this work, we investigate the case where $\mathbf{R}$ is the path measure of a diffusion process with killing, which we interpret as a regime-switching diffusion. In addition to matching the initial and terminal distributions of trajectories that survive up to time $T$, we consider a general constraint $ψ(t,x)$ on the distribution of killing times and/or killing locations. We investigate the uSBPs corresponding to four choices of $ψ$ in detail which reflect different levels of information available to an observer. We also provide a rigorous analysis of the connections and the comparisons among the outcomes of these four cases. Our results are novel in the field of uSBP. The regime-switching approach proposed in this work provides a unified framework for tackling different uSBP scenarios, which not only reconciles but also extends the existing literature on uSBP.
title A Regime-Switching Approach to the Unbalanced Schrödinger Bridge Problem
topic Probability
Optimization and Control
35Q93, 60H10, 60H30, 60J60, 93E20, 94A17
url https://arxiv.org/abs/2512.12971