FEAT: Free energy Estimators with Adaptive Transport

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: He, Jiajun, Du, Yuanqi, Vargas, Francisco, Wang, Yuanqing, Gomes, Carla P., Hernández-Lobato, José Miguel, Vanden-Eijnden, Eric
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915734909616128
author He, Jiajun
Du, Yuanqi
Vargas, Francisco
Wang, Yuanqing
Gomes, Carla P.
Hernández-Lobato, José Miguel
Vanden-Eijnden, Eric
author_facet He, Jiajun
Du, Yuanqi
Vargas, Francisco
Wang, Yuanqing
Gomes, Carla P.
Hernández-Lobato, José Miguel
Vanden-Eijnden, Eric
contents We present Free energy Estimators with Adaptive Transport (FEAT), a novel framework for free energy estimation -- a critical challenge across scientific domains. FEAT leverages learned transports implemented via stochastic interpolants and provides consistent, minimum-variance estimators based on escorted Jarzynski equality and controlled Crooks theorem, alongside variational upper and lower bounds on free energy differences. Unifying equilibrium and non-equilibrium methods under a single theoretical framework, FEAT establishes a principled foundation for neural free energy calculations. Experimental validation on toy examples, molecular simulations, and quantum field theory demonstrates improvements over existing learning-based methods. Our PyTorch implementation is available at https://github.com/jiajunhe98/FEAT.
format Preprint
id arxiv_https___arxiv_org_abs_2504_11516
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle FEAT: Free energy Estimators with Adaptive Transport
He, Jiajun
Du, Yuanqi
Vargas, Francisco
Wang, Yuanqing
Gomes, Carla P.
Hernández-Lobato, José Miguel
Vanden-Eijnden, Eric
Machine Learning
Chemical Physics
Computational Physics
We present Free energy Estimators with Adaptive Transport (FEAT), a novel framework for free energy estimation -- a critical challenge across scientific domains. FEAT leverages learned transports implemented via stochastic interpolants and provides consistent, minimum-variance estimators based on escorted Jarzynski equality and controlled Crooks theorem, alongside variational upper and lower bounds on free energy differences. Unifying equilibrium and non-equilibrium methods under a single theoretical framework, FEAT establishes a principled foundation for neural free energy calculations. Experimental validation on toy examples, molecular simulations, and quantum field theory demonstrates improvements over existing learning-based methods. Our PyTorch implementation is available at https://github.com/jiajunhe98/FEAT.
title FEAT: Free energy Estimators with Adaptive Transport
topic Machine Learning
Chemical Physics
Computational Physics
url https://arxiv.org/abs/2504.11516