Coupled Cluster con M\=oLe: Molecular Orbital Learning for Neural Wavefunctions

TL;DR

This paper introduces M ext= oLe, a machine learning model that predicts coupled-cluster excitation amplitudes directly from molecular orbitals, enabling faster and more data-efficient quantum chemistry calculations.

Contribution

The novel M ext= oLe architecture predicts CC excitation amplitudes from Hartree-Fock orbitals, improving efficiency and generalization in quantum chemistry simulations.

Findings

Demonstrates high data efficiency and out-of-distribution generalization

Reduces the number of cycles needed for CC convergence

Effective on larger molecules and off-equilibrium geometries

Abstract

Density functional theory (DFT) is the most widely used method for calculating molecular properties; however, its accuracy is often insufficient for quantitative predictions. Coupled-cluster (CC) theory is the most successful method for achieving accuracy beyond DFT and for predicting properties that closely align with experiment. It is known as the ''gold standard'' of quantum chemistry. Unfortunately, the high computational cost of CC limits its widespread applicability. In this work, we present the Molecular Orbital Learning (M\=oLe) architecture, an equivariant machine learning model that directly predicts CC's core mathematical objects, the excitation amplitudes, from the mean-field Hartree-Fock molecular orbitals as inputs. We test various aspects of our model and demonstrate its remarkable data efficiency and out-of-distribution generalization to larger molecules and off-equilibrium geometries, despite being trained only on small equilibrium geometries. Finally, we also examine its ability to reduce the number of cycles required to converge CC calculations. M\=oLe can set the foundations for high-accuracy wavefunction-based ML architectures to accelerate molecular design and complement force-field approaches.