The use of high-dimensional regression techniques from machine learning has significantly improved the quantitative accuracy of interatomic potentials.Atomic simulations can now plausibly target quantitative predictio...The use of high-dimensional regression techniques from machine learning has significantly improved the quantitative accuracy of interatomic potentials.Atomic simulations can now plausibly target quantitative predictions in a variety of settings,which has brought renewed interest in robust means to quantify uncertainties.In many practical settings where model complexity is constrained(e.g.,due to performance considerations),misspecification—the inability of any one choice of model parameters to exactly match all training data—is a key contributor to errors that is often disregarded.Here,we employ a recent misspecification-aware regression technique to quantify parameter uncertainties,which is then propagated to a broad range of phase and defect properties in tungsten.The propagation is performed through both brute-force resampling and implicit Taylor expansion.The propagated misspecification uncertainties robustly quantify and bound errors on a broad range of material properties.We demonstrate application to recent foundational machine learning interatomic potentials,accurately predicting and bounding errors in MACE-MPA-0 energy predictions across the diverse materials project database.展开更多
基金supported by the Laboratory Directed Research and Development program of Los Alamos National Laboratory under project number 20220063DRAPAS acknowledges the support from the US Department of Energy through the Exascale Computing Project (17-SC-20-SC)+2 种基金a collaborative effort of the U.S. Department of Energy Office of Science and the National Nuclear Security Administration, and through the G. T. Seaborg Institute under project number 20240478CR-GTSTDS gratefully acknowledges support from ANR grants ANR-19-CE46-0006-1, ANR-23-CE46-0006-1, IDRIS allocation A0120913455with IM, an Emergence@INP grant from the CNRS. Los Alamos National Laboratory is operated by Triad National Security, LLC, for the National Nuclear Security Administration of the U.S. Department of Energy (Contract No. 89233218CNA000001).
文摘The use of high-dimensional regression techniques from machine learning has significantly improved the quantitative accuracy of interatomic potentials.Atomic simulations can now plausibly target quantitative predictions in a variety of settings,which has brought renewed interest in robust means to quantify uncertainties.In many practical settings where model complexity is constrained(e.g.,due to performance considerations),misspecification—the inability of any one choice of model parameters to exactly match all training data—is a key contributor to errors that is often disregarded.Here,we employ a recent misspecification-aware regression technique to quantify parameter uncertainties,which is then propagated to a broad range of phase and defect properties in tungsten.The propagation is performed through both brute-force resampling and implicit Taylor expansion.The propagated misspecification uncertainties robustly quantify and bound errors on a broad range of material properties.We demonstrate application to recent foundational machine learning interatomic potentials,accurately predicting and bounding errors in MACE-MPA-0 energy predictions across the diverse materials project database.
