Reversible molecular simulation for training classical and machine learning force fields

Fuente: arXiv
Saved in:
Bibliographic Details
Main Author: Greener, Joe G
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916690166546432
author Greener, Joe G
author_facet Greener, Joe G
contents The next generation of force fields for molecular dynamics will be developed using a wealth of data. Training systematically with experimental data remains a challenge, however, especially for machine learning potentials. Differentiable molecular simulation calculates gradients of observables with respect to parameters through molecular dynamics trajectories. Here we improve this approach by explicitly calculating gradients using a reverse-time simulation with effectively constant memory cost and a computation count similar to the forward simulation. The method is applied to learn all-atom water and gas diffusion models with different functional forms, and to train a machine learning potential for diamond from scratch. Comparison to ensemble reweighting indicates that reversible simulation can provide more accurate gradients and train to match time-dependent observables.
format Preprint
id arxiv_https___arxiv_org_abs_2412_04374
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Reversible molecular simulation for training classical and machine learning force fields
Greener, Joe G
Biomolecules
The next generation of force fields for molecular dynamics will be developed using a wealth of data. Training systematically with experimental data remains a challenge, however, especially for machine learning potentials. Differentiable molecular simulation calculates gradients of observables with respect to parameters through molecular dynamics trajectories. Here we improve this approach by explicitly calculating gradients using a reverse-time simulation with effectively constant memory cost and a computation count similar to the forward simulation. The method is applied to learn all-atom water and gas diffusion models with different functional forms, and to train a machine learning potential for diamond from scratch. Comparison to ensemble reweighting indicates that reversible simulation can provide more accurate gradients and train to match time-dependent observables.
title Reversible molecular simulation for training classical and machine learning force fields
topic Biomolecules
url https://arxiv.org/abs/2412.04374