Divide-and-conquer potentials enable scalable and accurate predictions of forces and energies in atomistic systems
Claudio Zeni (International School for Advanced Studies, Microsoft Research Cambridge)
Andrea Anelli (F. Hoffmann-La Roche Ltd, École Polytechnique Fédérale de Lausanne)
Aldo Glielmo (Bank of Italy, International School for Advanced Studies)
Stefano de Gironcoli (International School for Advanced Studies)
K.R. Rossi (École Polytechnique Fédérale de Lausanne, TU Delft - Mechanical Engineering)
More Info
expand_more
Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.
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.