Learning molecular energies using localized graph kernels
Abstract
Recent machine learning methods make it possible to model potential energy of atomic configurations with chemicallevel accuracy (as calculated from ab initio calculations) and at speeds suitable for molecular dynamics simulation. Best performance is achieved when the known physical constraints are encoded in the machine learning models. For example, the atomic energy is invariant under global translations and rotations; it is also invariant to permutations of samespecies atoms. Although simple to state, these symmetries are complicated to encode into machine learning algorithms. In this paper, we present a machine learning approach based on graph theory that naturally incorporates translation, rotation, and permutation symmetries. Specifically, we use a random walk graph kernel to measure the similarity of two adjacency matrices, each of which represents a local atomic environment. This Graph Approximated Energy (GRAPE) approach is flexible and admits many possible extensions. We benchmark a simple version of GRAPE by predicting atomization energies on a standard dataset of organic molecules.
 Publication:

Journal of Chemical Physics
 Pub Date:
 March 2017
 DOI:
 10.1063/1.4978623
 arXiv:
 arXiv:1612.00193
 Bibcode:
 2017JChPh.146k4107F
 Keywords:

 Physics  Computational Physics;
 Computer Science  Machine Learning;
 Statistics  Machine Learning
 EPrint:
 The Journal of Chemical Physics, 146(11), 114107 (2017)