Sampling-free Inference for Ab-Initio Potential Energy Surface Networks

TL;DR

This paper introduces PlaNet, a framework that enables rapid, accurate inference of potential energy surfaces for molecules by replacing Monte Carlo integration with a surrogate model, significantly speeding up calculations for larger systems.

Contribution

The paper proposes a novel framework, PlaNet, that trains a surrogate model alongside neural wave functions to enable direct energy estimation, eliminating the need for Monte Carlo integration during inference.

Findings

PlaNet accelerates energy inference by 7 orders of magnitude for large molecules.

PESNet++ reduces energy prediction errors by up to 74%.

The approach enables modeling high-resolution energy surfaces for larger systems.

Abstract

Recently, it has been shown that neural networks not only approximate the ground-state wave functions of a single molecular system well but can also generalize to multiple geometries. While such generalization significantly speeds up training, each energy evaluation still requires Monte Carlo integration which limits the evaluation to a few geometries. In this work, we address the inference shortcomings by proposing the Potential learning from ab-initio Networks (PlaNet) framework, in which we simultaneously train a surrogate model in addition to the neural wave function. At inference time, the surrogate avoids expensive Monte-Carlo integration by directly estimating the energy, accelerating the process from hours to milliseconds. In this way, we can accurately model high-resolution multi-dimensional energy surfaces for larger systems that previously were unobtainable via neural wave functions. Finally, we explore an additional inductive bias by introducing physically-motivated restricted neural wave function models. We implement such a function with several additional improvements in the new PESNet++ model. In our experimental evaluation, PlaNet accelerates inference by 7 orders of magnitude for larger molecules like ethanol while preserving accuracy. Compared to previous energy surface networks, PESNet++ reduces energy errors by up to 74%.