English

Efficient nonparametric $n$-body force fields from machine learning

Computational Physics 2018-05-30 v2

Abstract

We provide a definition and explicit expressions for nn-body Gaussian Process (GP) kernels which can learn any interatomic interaction occurring in a physical system, up to nn-body contributions, for any value of nn. The series is complete, as it can be shown that the "universal approximator" squared exponential kernel can be written as a sum of nn-body kernels. These recipes enable the choice of optimally efficient force models for each target system, as confirmed by extensive testing on various materials. We furthermore describe how the nn-body kernels can be "mapped" on equivalent representations that provide database-size-independent predictions and are thus crucially more efficient. We explicitly carry out this mapping procedure for the first non-trivial (3-body) kernel of the series, and show that this reproduces the GP-predicted forces with meV/A˚\text{meV/} \AA accuracy while being orders of magnitude faster. These results open the way to using novel force models (here named "M-FFs") that are computationally as fast as their corresponding standard parametrised nn-body force fields, while retaining the nonparametric character, the ease of training and validation, and the accuracy of the best recently proposed machine learning potentials.

Keywords

Cite

@article{arxiv.1801.04823,
  title  = {Efficient nonparametric $n$-body force fields from machine learning},
  author = {Aldo Glielmo and Claudio Zeni and Alessandro De Vita},
  journal= {arXiv preprint arXiv:1801.04823},
  year   = {2018}
}

Comments

13 pages, 8 captioned figures

R2 v1 2026-06-22T23:45:22.081Z