Issue 1, 2024

Divide-and-conquer potentials enable scalable and accurate predictions of forces and energies in atomistic systems

Abstract

In committee of experts strategies, small datasets are extracted from a larger one and utilised for the training of multiple models. These models' predictions are then carefully weighted so as to obtain estimates which are dominated by the model(s) that are most informed in each domain of the data manifold. Here, we show how this divide-and-conquer philosophy provides an avenue in the making of machine learning potentials for atomistic systems, which is general across systems of different natures and efficiently scalable by construction. We benchmark this approach on various datasets and demonstrate that divide-and-conquer linear potentials are more accurate than their single model counterparts, while incurring little to no extra computational cost.

Graphical abstract: Divide-and-conquer potentials enable scalable and accurate predictions of forces and energies in atomistic systems

Article information

Article type
Paper
Submitted
17 Aug 2023
Accepted
14 Nov 2023
First published
15 Nov 2023
This article is Open Access
Creative Commons BY license

Digital Discovery, 2024,3, 113-121

Divide-and-conquer potentials enable scalable and accurate predictions of forces and energies in atomistic systems

C. Zeni, A. Anelli, A. Glielmo, S. de Gironcoli and K. Rossi, Digital Discovery, 2024, 3, 113 DOI: 10.1039/D3DD00155E

This article is licensed under a Creative Commons Attribution 3.0 Unported Licence. You can use material from this article in other publications without requesting further permissions from the RSC, provided that the correct acknowledgement is given.

Read more about how to correctly acknowledge RSC content.

Social activity

Spotlight

Advertisements