Riemannian Stochastic Interpolants for Amorphous Particle Systems

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Grenioux, Louis, Galliano, Leonardo, Berthier, Ludovic, Biroli, Giulio, Gabrié, Marylou
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918254857945088
author Grenioux, Louis
Galliano, Leonardo
Berthier, Ludovic
Biroli, Giulio
Gabrié, Marylou
author_facet Grenioux, Louis
Galliano, Leonardo
Berthier, Ludovic
Biroli, Giulio
Gabrié, Marylou
contents Modern generative models hold great promise for accelerating diverse tasks involving the simulation of physical systems, but they must be adapted to the specific constraints of each domain. Significant progress has been made for biomolecules and crystalline materials. Here, we address amorphous materials (glasses), which are disordered particle systems lacking atomic periodicity. Sampling equilibrium configurations of glass-forming materials is a notoriously slow and difficult task. This obstacle could be overcome by developing a generative framework capable of producing equilibrium configurations with well-defined likelihoods. In this work, we address this challenge by leveraging an equivariant Riemannian stochastic interpolation framework which combines Riemannian stochastic interpolant and equivariant flow matching. Our method rigorously incorporates periodic boundary conditions and the symmetries of multi-component particle systems, adapting an equivariant graph neural network to operate directly on the torus. Our numerical experiments on model amorphous systems demonstrate that enforcing geometric and symmetry constraints significantly improves generative performance.
format Preprint
id arxiv_https___arxiv_org_abs_2512_16607
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Riemannian Stochastic Interpolants for Amorphous Particle Systems
Grenioux, Louis
Galliano, Leonardo
Berthier, Ludovic
Biroli, Giulio
Gabrié, Marylou
Machine Learning
Statistical Mechanics
Computational Physics
Modern generative models hold great promise for accelerating diverse tasks involving the simulation of physical systems, but they must be adapted to the specific constraints of each domain. Significant progress has been made for biomolecules and crystalline materials. Here, we address amorphous materials (glasses), which are disordered particle systems lacking atomic periodicity. Sampling equilibrium configurations of glass-forming materials is a notoriously slow and difficult task. This obstacle could be overcome by developing a generative framework capable of producing equilibrium configurations with well-defined likelihoods. In this work, we address this challenge by leveraging an equivariant Riemannian stochastic interpolation framework which combines Riemannian stochastic interpolant and equivariant flow matching. Our method rigorously incorporates periodic boundary conditions and the symmetries of multi-component particle systems, adapting an equivariant graph neural network to operate directly on the torus. Our numerical experiments on model amorphous systems demonstrate that enforcing geometric and symmetry constraints significantly improves generative performance.
title Riemannian Stochastic Interpolants for Amorphous Particle Systems
topic Machine Learning
Statistical Mechanics
Computational Physics
url https://arxiv.org/abs/2512.16607