Learning collective variables that respect permutational symmetry

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yuan, Jiaxin, Sule, Shashank, Lam, Yeuk Yin, Cameron, Maria
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908428864061440
author Yuan, Jiaxin
Sule, Shashank
Lam, Yeuk Yin
Cameron, Maria
author_facet Yuan, Jiaxin
Sule, Shashank
Lam, Yeuk Yin
Cameron, Maria
contents In addition to translational and rotational symmetries, clusters of identical interacting particles possess permutational symmetry. Coarse-grained models for such systems are instrumental in identifying metastable states, providing an effective description of their dynamics, and estimating transition rates. We propose a numerical framework for learning collective variables that respect translational, rotational, and permutational symmetries, and for estimating transition rates and residence times. It combines a sort-based featurization, residence manifold learning in the feature space, and learning collective variables with autoencoders whose loss function utilizes the orthogonality relationship (Legoll and Lelievre, 2010). The committor of the resulting reduced model is used as the reaction coordinate in the forward flux sampling and to design a control for sampling the transition path process. We offer two case studies, the Lennard-Jones-7 in 2D and the Lennard-Jones-8 in 3D. The transition rates and residence times computed with the aid of the reduced models agree with those obtained via brute-force methods.
format Preprint
id arxiv_https___arxiv_org_abs_2507_00408
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Learning collective variables that respect permutational symmetry
Yuan, Jiaxin
Sule, Shashank
Lam, Yeuk Yin
Cameron, Maria
Chemical Physics
Numerical Analysis
82B31, 60G99, 70F99
In addition to translational and rotational symmetries, clusters of identical interacting particles possess permutational symmetry. Coarse-grained models for such systems are instrumental in identifying metastable states, providing an effective description of their dynamics, and estimating transition rates. We propose a numerical framework for learning collective variables that respect translational, rotational, and permutational symmetries, and for estimating transition rates and residence times. It combines a sort-based featurization, residence manifold learning in the feature space, and learning collective variables with autoencoders whose loss function utilizes the orthogonality relationship (Legoll and Lelievre, 2010). The committor of the resulting reduced model is used as the reaction coordinate in the forward flux sampling and to design a control for sampling the transition path process. We offer two case studies, the Lennard-Jones-7 in 2D and the Lennard-Jones-8 in 3D. The transition rates and residence times computed with the aid of the reduced models agree with those obtained via brute-force methods.
title Learning collective variables that respect permutational symmetry
topic Chemical Physics
Numerical Analysis
82B31, 60G99, 70F99
url https://arxiv.org/abs/2507.00408