Stability-Aware Training of Neural Network Interatomic Potentials with Differentiable Boltzmann Estimators

arXiv:2402.13984v1 Announce Type: new
Abstract: Neural network interatomic potentials (NNIPs) are an attractive alternative to ab-initio methods for molecular dynamics (MD) simulations. However, they can produce unstable simulations which sample unphysical states, limiting their usefulness for modeling phenomena occurring over longer timescales. To address these challenges, we present Stability-Aware Boltzmann Estimator (StABlE) Training, a multi-modal training procedure which combines conventional supervised training from quantum-mechanical energies and forces with reference system observables, to produce stable and accurate NNIPs. StABlE Training iteratively …

abstract arxiv boltzmann challenges cond-mat.dis-nn cond-mat.mtrl-sci cs.lg differentiable dynamics modeling molecular dynamics network neural network physics.chem-ph physics.comp-ph sample simulations stability training type