Enabling ab initio geometry optimization of strongly correlated systems with transferable deep quantum Monte Carlo

TL;DR

This paper introduces a transferable deep-learning variational Monte Carlo framework for accurate, efficient ab initio exploration of complex potential energy surfaces in strongly correlated molecular systems, enabling detailed studies of chemical reactions.

Contribution

It combines deep-learning VMC with Gaussian process regression to accurately sample and characterize PESs across geometries, including transition states and excited states, with minimal computational cost.

Findings

Achieves zero-shot chemical accuracy in PES sampling.

Enables efficient exploration of complex PES landscapes.

Supports studies of bond breaking and formation in multi-reference systems.

Abstract

A faithful description of chemical processes requires exploring extended regions of the molecular potential energy surface (PES), which remains challenging for strongly correlated systems. Transferable deep-learning variational Monte Carlo (VMC) offers a promising route by efficiently solving the electronic Schr\"odinger equation jointly across molecular geometries at consistently high accuracy, yet its stochastic nature renders direct exploration of molecular configuration space nontrivial. Here, we present a framework for highly accurate ab initio exploration of PESs that combines transferable deep-learning VMC with a cost-effective estimation of energies, forces, and Hessians. By continuously sampling nuclear configurations during VMC optimization of electronic wave functions, we obtain transferable descriptions that achieve zero-shot chemical accuracy within chemically relevant distributions of molecular geometries. Throughout the subsequent characterization of molecular configuration space, the PES is evaluated only sparsely, with local approximations constructed by estimating VMC energies and forces at sampled geometries and aggregating the resulting noisy data using Gaussian process regression. Our method enables accurate and efficient exploration of complex PES landscapes, including structure relaxation, transition-state searches, and minimum-energy pathways, for both ground and excited states. This opens the door to studying bond breaking, formation, and large structural rearrangements in systems with pronounced multi-reference character.