no code implementations • 1 Feb 2024 • Joshua A. Vita, Amit Samanta, Fei Zhou, Vincenzo Lordi
Though in this work we focus on the use of LTAU with deep learning atomistic force fields, we emphasize that it can be readily applied to any regression task, or any ensemble-generation technique, to provide a reliable and easy-to-implement UQ metric.
no code implementations • 4 Oct 2023 • Joshua A. Vita, Dallas R. Trinkle
While machine learning (ML) interatomic potentials (IPs) are able to achieve accuracies nearing the level of noise inherent in the first-principles data to which they are trained, it remains to be shown if their increased complexities are strictly necessary for constructing high-quality IPs.
no code implementations • 12 Feb 2023 • Joshua A. Vita, Daniel Schwalbe-Koda
In this work, we show how architectural and optimization choices influence the generalization of NNIPs, revealing trends in molecular dynamics (MD) stability, data efficiency, and loss landscapes.