Wavelet Scattering Regression of Quantum Chemical Energies

Abstract

We introduce multiscale invariant dictionaries to estimate quantum chemical energies of organic molecules, from training databases. Molecular energies are invariant to isometric atomic displacements, and are Lipschitz continuous to molecular deformations. Similarly to density functional theory (DFT), the molecule is represented by an electronic density function. A multiscale invariant dictionary is calculated with wavelet scattering invariants. It cascades a first wavelet transform which separates scales, with a second wavelet transform which computes interactions across scales. Sparse scattering regressions give state of the art results over two databases of organic planar molecules. On these databases, the regression error is of the order of the error produced by DFT codes, but at a fraction of the computational cost.

Replaces arXiv:1502.02077. v2: Minor clarifications, additions, and typo corrections. v3: Minor edits. Software to reproduce the numerical results is available at: https://github.com/matthew-hirn/ScatNet-QM-2D

References in corpus (6)

• Sparsity and Incoherence in Compressive Sampling
• Comparing molecules and solids across structural and alchemical space
• SCAN-based hybrid and double-hybrid density functionals from models without fitted parameters
• A fingerprint based metric for measuring similarities of crystalline structures
• Comment on "Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning"
• Adaptive Multi-resolution 3D Hartree-Fock-Bogoliubov Solver for Nuclear Structure

Cited by in corpus (20)

• SchNet - a deep learning architecture for molecules and materials
• Machine Learning Force Fields
• Deep learning for molecular design - a review of the state of the art
• Machine learning a general purpose interatomic potential for silicon
• Deep Learning of Vortex Induced Vibrations
• Understanding molecular representations in machine learning: The role of uniqueness and target similarity
• Incorporating long-range physics in atomic-scale machine learning
• Atom-Density Representations for Machine Learning
• Representations of molecules and materials for interpolation of quantum-mechanical simulations via machine learning
• Data-driven rogue waves and parameter discovery in the defocusing NLS equation with a potential using the PINN deep learning
• A new approach to observational cosmology using the scattering transform
• Solid Harmonic Wavelet Scattering for Predictions of Molecule Properties
• PANNA: Properties from Artificial Neural Network Architectures
• Detection of Topological Materials with Machine Learning
• Classification of Magnetohydrodynamic Simulations using Wavelet Scattering Transforms
• Wavelet Scattering Networks for Atomistic Systems with Extrapolation of Material Properties
• Statistical learning of geometric characteristics of wireless networks
• Maximum volume simplex method for automatic selection and classification of atomic environments and environment descriptor compression
• On Generalizations of the Nonwindowed Scattering Transform
• Energy Propagation in Scattering Convolution Networks Can Be Arbitrarily Slow