Solid harmonic wavelet scattering for predictions of molecule properties
Abstract
We present a machine learning algorithm for the prediction of molecule properties inspired by ideas from density functional theory (DFT). Using Gaussian-type orbital functions, we create surrogate electronic densities of the molecule from which we compute invariant “solid harmonic scattering coefficients” that account for different types of interactions at different scales. Multilinear regressions of various physical properties of molecules are computed from these invariant coefficients. Numerical experiments show that these regressions have near state-of-the-art performance, even with relatively few training examples. Predictions over small sets of scattering coefficients can reach a DFT precision while being interpretable.
Document Details
- Document Type
- Pub Defense Publication
- Publication Date
- May 14, 2018
- Source ID
- 10.1063/1.5023798
Entities
People
- Georgios Exarchakis
- Louis Thiry
- Matthew Hirn
- Michael Eickenberg
- Stephane Mallat
Organizations
- Alfred P. Sloan Foundation
- Defense Advanced Research Projects Agency
- FP7 Ideas: European Research Council
- Michigan State University
- National Science Foundation Directorate for Mathematical & Physical Sciences
- École Normale Supérieure