Application-specific machine-learned interatomic potentials: exploring the trade-off between DFT convergence, MLIP expressivity, and computational cost

TL;DR

This paper investigates how to optimize the training process of machine-learned interatomic potentials to balance accuracy, computational cost, and model complexity, using a beryllium dataset and spectral neighbor analysis.

Contribution

It demonstrates that joint optimization of training parameters and model complexity can significantly reduce the overall computational cost of MLIP development.

Findings

Joint optimization reduces training and evaluation costs

Training set selection impacts MLIP accuracy and efficiency

Model complexity influences the trade-off between cost and performance

Abstract

Machine-learned interatomic potentials (MLIPs) are revolutionizing computational materials science and chemistry by offering an efficient alternative to {\em ab initio} molecular dynamics (MD) simulations. However, fitting high-quality MLIPs remains a challenging, time-consuming, and computationally intensive task where numerous trade-offs have to be considered, e.g., How much and what kind of atomic configurations should be included in the training set? Which level of {\em ab initio} convergence should be used to generate the training set? Which loss function should be used for fitting the MLIP? Which machine learning architecture should be used to train the MLIP? The answers to these questions significantly impact both the computational cost of MLIP training and the accuracy and computational cost of subsequent MLIP MD simulations. In this study, we use a configurationally diverse beryllium dataset and quadratic spectral neighbor analysis potential. We demonstrate that joint optimization of energy versus force weights, training set selection strategies, and convergence settings of the {\em ab initio} reference simulations, as well as model complexity can lead to a significant reduction in the overall computational cost associated with training and evaluating MLIPs. This opens the door to computationally efficient generation of high-quality MLIPs for a range of applications which demand different accuracy versus training and evaluation cost trade-offs.