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

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

Zeni, Claudio (Microsoft Research Cambridge; International School for Advanced Studies)
Anelli, Andrea (F. Hoffmann-La Roche Ltd; École Polytechnique Fédérale de Lausanne)
Glielmo, Aldo (International School for Advanced Studies; Bank of Italy)
de Gironcoli, Stefano (International School for Advanced Studies)
Rossi, K.R. (TU Delft Team Marcel Sluiter; École Polytechnique Fédérale de Lausanne)

2023

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.

http://resolver.tudelft.nl/uuid:76d5316f-31c1-4649-9836-855c0ed9fc8c

https://doi.org/10.1039/d3dd00155e

2635-098X

Digital Discovery, 3 (2024) (1), 113-121

Institutional Repository

journal article

© 2023 Claudio Zeni, Andrea Anelli, Aldo Glielmo, Stefano de Gironcoli, K.R. Rossi