Population Annealing as a Discrete-Time Schrödinger Bridge

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteur principal: Ohzeki, Masayuki
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866917348862066688
author Ohzeki, Masayuki
author_facet Ohzeki, Masayuki
contents We present a theoretical framework that reinterprets Population Annealing (PA) through the lens of the discrete-time Schrödinger Bridge (SB) problem. We demonstrate that the heuristic reweighting step in PA is derived by analytically solving the Schrödinger system without iterative computation via instantaneous projection. In addition, we identify the thermodynamic work as the optimal control potential that solves the global variational problem on path space. This perspective unifies non-equilibrium thermodynamics with the geometric framework of optimal transport, interpreting the Jarzynski equality as a consistency condition within the Donsker-Varadhan variational principle, and elucidates the thermodynamic optimality of PA.
format Preprint
id arxiv_https___arxiv_org_abs_2603_16056
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Population Annealing as a Discrete-Time Schrödinger Bridge
Ohzeki, Masayuki
Statistical Mechanics
Quantum Physics
Machine Learning
We present a theoretical framework that reinterprets Population Annealing (PA) through the lens of the discrete-time Schrödinger Bridge (SB) problem. We demonstrate that the heuristic reweighting step in PA is derived by analytically solving the Schrödinger system without iterative computation via instantaneous projection. In addition, we identify the thermodynamic work as the optimal control potential that solves the global variational problem on path space. This perspective unifies non-equilibrium thermodynamics with the geometric framework of optimal transport, interpreting the Jarzynski equality as a consistency condition within the Donsker-Varadhan variational principle, and elucidates the thermodynamic optimality of PA.
title Population Annealing as a Discrete-Time Schrödinger Bridge
topic Statistical Mechanics
Quantum Physics
Machine Learning
url https://arxiv.org/abs/2603.16056