Optimal radial basis for density-based atomic representations

Abstract

The input of almost every machine learning algorithm targeting the properties of matter at the atomic scale involves a transformation of the list of Cartesian atomic coordinates into a more symmetric representation. Many of the most popular representations can be seen as an expansion of the symmetrized correlations of the atom density, and differ mainly by the choice of basis. Considerable effort has been dedicated to the optimization of the basis set, typically driven by heuristic considerations on the behavior of the regression target. Here we take a different, unsupervised viewpoint, aiming to determine the basis that encodes in the most compact way possible the structural information that is relevant for the dataset at hand. For each training dataset and number of basis functions, one can determine a unique basis that is optimal in this sense, and can be computed at no additional cost with respect to the primitive basis by approximating it with splines. We demonstrate that this construction yields representations that are accurate and computationally efficient, particularly when constructing representations that correspond to high-body order correlations. We present examples that involve both molecular and condensed-phase machine-learning models.

References in corpus (24)

• Gaussian Approximation Potentials: the accuracy of quantum mechanics, without the electrons
• On representing chemical environments
• Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning
• Moment Tensor Potentials: a class of systematically improvable interatomic potentials
• A Performance and Cost Assessment of Machine Learning Interatomic Potentials
• DScribe: Library of Descriptors for Machine Learning in Materials Science
• Machine Learning Unifies the Modelling of Materials and Molecules
• Machine learning prediction errors better than DFT accuracy
• Physics-inspired structural representations for molecules and materials
• Machine learning a general purpose interatomic potential for silicon
• Symmetry-Adapted Machine-Learning for Tensorial Properties of Atomistic Systems
• Automatic Selection of Atomic Fingerprints and Reference Configurations for Machine-Learning Potentials
• Understanding molecular representations in machine learning: The role of uniqueness and target similarity
• Accurate Interatomic Force Fields via Machine Learning with Covariant Kernels
• On the Completeness of Atomic Structure Representations
• Atom-Density Representations for Machine Learning
• Optimizing many-body atomic descriptors for enhanced computational performance of machine learning based interatomic potentials
• Feature Optimization for Atomistic Machine Learning Yields A Data-Driven Construction of the Periodic Table of the Elements
• Cormorant: Covariant Molecular Neural Networks
• Recursive evaluation and iterative contraction of $N$-body equivariant features
• Efficient implementation of atom-density representations
• An assessment of the structural resolution of various fingerprints commonly used in machine learning
• Relevance of Rotationally Equivariant Convolutions for Predicting Molecular Properties
• Sensitivity and Dimensionality of Atomic Environment Representations used for Machine Learning Interatomic Potentials

Cited by in corpus (9)

• Equivariant representations for molecular Hamiltonians and N-center atomic-scale properties
• Tensor-reduced atomic density representations
• Through the eyes of a descriptor: Constructing complete, invertible descriptions of atomic environments
• Ranking the Synthesizability of Hypothetical Zeolites with the Sorting Hat
• A smooth basis for atomistic machine learning
• Comment on "Manifolds of quasi-constant SOAP and ACSF fingerprints and the resulting failure to machine learn four body interactions"
• Unified theory of atom-centered representations and message-passing machine-learning schemes
• Compressing local atomic neighbourhood descriptors
• Machine learning of electronic structure and atomistic properties from the external potential