Enregistré dans:
Détails bibliographiques
Auteurs principaux: Huang, Shengjie, Yang, Sijie, Yi, Jianqiao, Zheng, Rui, Liao, Haocong, Hussain, Muzammal, Tu, Yaoquan, Lu, Xiaoyun, Zhou, Yang
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:https://arxiv.org/abs/2603.18076
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866912973541343232
author Huang, Shengjie
Yang, Sijie
Yi, Jianqiao
Zheng, Rui
Liao, Haocong
Hussain, Muzammal
Tu, Yaoquan
Lu, Xiaoyun
Zhou, Yang
author_facet Huang, Shengjie
Yang, Sijie
Yi, Jianqiao
Zheng, Rui
Liao, Haocong
Hussain, Muzammal
Tu, Yaoquan
Lu, Xiaoyun
Zhou, Yang
contents Replica exchange (REX) is one of the most widely used enhanced sampling methodologies, yet its efficiency is limited by the requirement for a large number of intermediate temperature replicas. Here we present Generative Replica Exchange (GREX), which integrates deep generative models into the REX framework to eliminate this temperature ladder. Drawing inspiration from reservoir replica exchange (res-REX), GREX utilizes trained normalizing flows to generate high-temperature configurations on demand and map them directly to the target distribution using the potential energy as a constraint, without requiring target-temperature training data. This approach reduces production simulations to a single replica at the target temperature while maintaining thermodynamic rigor through Metropolis exchange acceptance. We validate GREX on three benchmark systems of increasing complexity, highlighting its superior efficiency and practical applicability for molecular simulations.
format Preprint
id arxiv_https___arxiv_org_abs_2603_18076
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Generative Replica-Exchange: A Flow-based Framework for Accelerating Replica Exchange Simulations
Huang, Shengjie
Yang, Sijie
Yi, Jianqiao
Zheng, Rui
Liao, Haocong
Hussain, Muzammal
Tu, Yaoquan
Lu, Xiaoyun
Zhou, Yang
Biomolecules
Machine Learning
Computational Physics
Replica exchange (REX) is one of the most widely used enhanced sampling methodologies, yet its efficiency is limited by the requirement for a large number of intermediate temperature replicas. Here we present Generative Replica Exchange (GREX), which integrates deep generative models into the REX framework to eliminate this temperature ladder. Drawing inspiration from reservoir replica exchange (res-REX), GREX utilizes trained normalizing flows to generate high-temperature configurations on demand and map them directly to the target distribution using the potential energy as a constraint, without requiring target-temperature training data. This approach reduces production simulations to a single replica at the target temperature while maintaining thermodynamic rigor through Metropolis exchange acceptance. We validate GREX on three benchmark systems of increasing complexity, highlighting its superior efficiency and practical applicability for molecular simulations.
title Generative Replica-Exchange: A Flow-based Framework for Accelerating Replica Exchange Simulations
topic Biomolecules
Machine Learning
Computational Physics
url https://arxiv.org/abs/2603.18076