Learning Macroscopic Dynamics from Partial Microscopic Observations

TL;DR

This paper introduces a novel method to learn macroscopic system dynamics efficiently from limited microscopic force data, leveraging sparsity assumptions to reduce computational costs and improve robustness.

Contribution

It proposes a new approach that maps macroscopic learning tasks to microscopic coordinates using partial force observations, with theoretical justification and practical validation.

Findings

Accurately learns macroscopic dynamics with partial microscopic data

Reduces computational cost of force evaluations

Demonstrates robustness across different microscopic models

Abstract

Macroscopic observables of a system are of keen interest in real applications such as the design of novel materials. Current methods rely on microscopic trajectory simulations, where the forces on all microscopic coordinates need to be computed or measured. However, this can be computationally prohibitive for realistic systems. In this paper, we propose a method to learn macroscopic dynamics requiring only force computations on a subset of the microscopic coordinates. Our method relies on a sparsity assumption: the force on each microscopic coordinate relies only on a small number of other coordinates. The main idea of our approach is to map the training procedure on the macroscopic coordinates back to the microscopic coordinates, on which partial force computations can be used as stochastic estimation to update model parameters. We provide a theoretical justification of this under suitable conditions. We demonstrate the accuracy, force computation efficiency, and robustness of our method on learning macroscopic closure models from a variety of microscopic systems, including those modeled by partial differential equations or molecular dynamics simulations.