Optimal radial basis for density-based atomic representations
- 9 September 2021
- journal article
- conference paper
- Published by AIP Publishing in The Journal of Chemical Physics
- Vol. 155 (10) , 104106
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 build 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 working with representations that correspond to high-body order correlations. We present examples that involve both molecular and condensed-phase machine-learning models.Keywords
All Related Versions
Funding Information
- National Center of Competence in Research Materials’ Revolution: Computational Design and Discovery of Novel Materials (DD1)
- Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung (200021-182057)
This publication has 36 references indexed in Scilit:
- Demonstrating the Transferability and the Descriptive Power of Sketch-MapJournal of Chemical Theory and Computation, 2013
- Neural network potential-energy surfaces in chemistry: a tool for large-scale simulationsPhysical Chemistry Chemical Physics, 2011
- Gaussian Approximation Potentials: The Accuracy of Quantum Mechanics, without the ElectronsPhysical Review Letters, 2010
- Ab initio molecular simulations with numeric atom-centered orbitalsComputer Physics Communications, 2009
- Permutationally invariant potential energy surfaces in high dimensionalityInternational Reviews in Physical Chemistry, 2009
- Generalized Neural-Network Representation of High-Dimensional Potential-Energy SurfacesPhysical Review Letters, 2007
- The farthest point strategy for progressive image samplingIEEE Transactions on Image Processing, 1997
- Fully optimized contracted Gaussian basis sets for atoms Li to KrThe Journal of Chemical Physics, 1992
- Principal covariates regressionChemometrics and Intelligent Laboratory Systems, 1992
- Generalized cluster description of multicomponent systemsPhysica A: Statistical Mechanics and its Applications, 1984