Operators in Machine Learning: Response Properties in Chemical Space

TL;DR

This paper explores the application of response operators in quantum machine learning models to predict molecular response properties, demonstrating systematic accuracy improvements and practical chemical applications.

Contribution

It introduces a theoretical framework for using response operators in quantum ML models and provides numerical evidence of their effectiveness in predicting molecular response properties.

Findings

Prediction errors decrease with larger training sets.

High accuracy achieved for atomic forces and dipole moments.

Successful prediction of normal modes and IR spectra.

Abstract

The role of response operators is well established in quantum mechanics. We investigate their use for universal quantum machine learning models of response properties in molecules. After introducing a theoretical basis, we present and discuss numerical evidence based on measuring the potential energy's response with respect to atomic displacement and to electric fields. Prediction errors for corresponding properties, atomic forces and dipole moments, improve in a systematic fashion with training set size and reach high accuracy for small training sets. Prediction of normal modes and IR-spectra of some small molecules demonstrates the usefulness of this approach for chemistry.