Reducing the Quantum Many-electron Problem to Two Electrons with Machine Learning

TL;DR

This paper introduces a machine learning approach that predicts two-electron wave function contributions to efficiently approximate the energies of larger molecules, significantly reducing computational complexity in electronic structure calculations.

Contribution

The authors develop a neural network model that learns geminal-occupation distributions, enabling reduction of the many-electron problem to a two-electron problem for larger molecules.

Findings

Successfully predicts energies of hydrocarbons with 8-15 carbons

Learns N-representability conditions for electron distributions

Reduces computational complexity in electronic structure calculations

Abstract

An outstanding challenge in chemical computation is the many-electron problem where computational methodologies scale prohibitively with system size. The energy of any molecule can be expressed as a weighted sum of the energies of two-electron wave functions that are computable from only a two-electron calculation. Despite the physical elegance of this extended ``aufbau'' principle, the determination of the distribution of weights -- geminal occupations -- for general molecular systems has remained elusive. Here we introduce a new paradigm for electronic structure where approximate geminal-occupation distributions are ``learned'' via a convolutional neural network. We show that the neural network learns the $N$-representability conditions, constraints on the distribution for it to represent an $N$-electron system. By training on hydrocarbon isomers with only 2-7 carbon atoms, we are able to predict the energies for isomers of octane as well as hydrocarbons with 8-15 carbons. The present work demonstrates that machine learning can be used to reduce the many-electron problem to an effective two-electron problem, opening new opportunities for accurately predicting electronic structure.