Generative Replica-Exchange: A Flow-based Framework for Accelerating Replica Exchange Simulations

TL;DR

GREX integrates deep generative models into replica exchange simulations to eliminate the need for multiple temperature replicas, significantly improving efficiency while maintaining thermodynamic accuracy.

Contribution

This paper introduces GREX, a novel flow-based framework that uses trained normalizing flows to generate configurations on demand, reducing the number of replicas needed in replica exchange methods.

Findings

GREX achieves higher efficiency than traditional REX methods.

GREX maintains thermodynamic rigor through Metropolis acceptance.

Validated on three benchmark systems of increasing complexity.

Abstract

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.