Analyzing multimodal probability measures with autoencoders

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Lelièvre, Tony, Pigeon, Thomas, Stoltz, Gabriel, Zhang, Wei
Formato: Preprint
Publicado: 2023
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866910366582177792
author Lelièvre, Tony
Pigeon, Thomas
Stoltz, Gabriel
Zhang, Wei
author_facet Lelièvre, Tony
Pigeon, Thomas
Stoltz, Gabriel
Zhang, Wei
contents Finding collective variables to describe some important coarse-grained information on physical systems, in particular metastable states, remains a key issue in molecular dynamics. Recently, machine learning techniques have been intensively used to complement and possibly bypass expert knowledge in order to construct collective variables. Our focus here is on neural network approaches based on autoencoders. We study some relevant mathematical properties of the loss function considered for training autoencoders, and provide physical interpretations based on conditional variances and minimum energy paths. We also consider various extensions in order to better describe physical systems, by incorporating more information on transition states at saddle points, and/or allowing for multiple decoders in order to describe several transition paths. Our results are illustrated on toy two dimensional systems and on alanine dipeptide.
format Preprint
id arxiv_https___arxiv_org_abs_2310_03492
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Analyzing multimodal probability measures with autoencoders
Lelièvre, Tony
Pigeon, Thomas
Stoltz, Gabriel
Zhang, Wei
Chemical Physics
Statistical Mechanics
Finding collective variables to describe some important coarse-grained information on physical systems, in particular metastable states, remains a key issue in molecular dynamics. Recently, machine learning techniques have been intensively used to complement and possibly bypass expert knowledge in order to construct collective variables. Our focus here is on neural network approaches based on autoencoders. We study some relevant mathematical properties of the loss function considered for training autoencoders, and provide physical interpretations based on conditional variances and minimum energy paths. We also consider various extensions in order to better describe physical systems, by incorporating more information on transition states at saddle points, and/or allowing for multiple decoders in order to describe several transition paths. Our results are illustrated on toy two dimensional systems and on alanine dipeptide.
title Analyzing multimodal probability measures with autoencoders
topic Chemical Physics
Statistical Mechanics
url https://arxiv.org/abs/2310.03492