Exploring the design space of machine-learning models for quantum chemistry with a fully differentiable framework

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Suman, Divya, Nigam, Jigyasa, Saade, Sandra, Pegolo, Paolo, Tuerk, Hanna, Zhang, Xing, Chan, Garnet Kin-Lic, Ceriotti, Michele
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916810436116480
author Suman, Divya
Nigam, Jigyasa
Saade, Sandra
Pegolo, Paolo
Tuerk, Hanna
Zhang, Xing
Chan, Garnet Kin-Lic
Ceriotti, Michele
author_facet Suman, Divya
Nigam, Jigyasa
Saade, Sandra
Pegolo, Paolo
Tuerk, Hanna
Zhang, Xing
Chan, Garnet Kin-Lic
Ceriotti, Michele
contents Traditional atomistic machine learning (ML) models serve as surrogates for quantum mechanical (QM) properties, predicting quantities such as dipole moments and polarizabilities, directly from compositions and geometries of atomic configurations. With the emergence of ML approaches to predict the "ingredients" of a QM calculation, such as the ground state charge density or the effective single-particle Hamiltonian, it has become possible to obtain multiple properties through analytical physics-based operations on these intermediate ML predictions. We present a framework to seamlessly integrate the prediction of an effective electronic Hamiltonian, for both molecular and condensed-phase systems, with PySCFAD, a differentiable QM workflow that facilitates its indirect training against functions of the Hamiltonian, such as electronic energy levels, dipole moments, polarizability, etc. We then use this framework to explore various possible choices within the design space of hybrid ML/QM models, examining the influence of incorporating multiple targets on model performance and learning a reduced-basis ML Hamiltonian that can reproduce targets computed from a much larger basis. Our benchmarks evaluate the accuracy and transferability of these hybrid models, compare them against predictions of atomic properties from their surrogate models, and provide indications to guide the design of the interface between the ML and QM components of the model.
format Preprint
id arxiv_https___arxiv_org_abs_2504_01187
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Exploring the design space of machine-learning models for quantum chemistry with a fully differentiable framework
Suman, Divya
Nigam, Jigyasa
Saade, Sandra
Pegolo, Paolo
Tuerk, Hanna
Zhang, Xing
Chan, Garnet Kin-Lic
Ceriotti, Michele
Chemical Physics
Traditional atomistic machine learning (ML) models serve as surrogates for quantum mechanical (QM) properties, predicting quantities such as dipole moments and polarizabilities, directly from compositions and geometries of atomic configurations. With the emergence of ML approaches to predict the "ingredients" of a QM calculation, such as the ground state charge density or the effective single-particle Hamiltonian, it has become possible to obtain multiple properties through analytical physics-based operations on these intermediate ML predictions. We present a framework to seamlessly integrate the prediction of an effective electronic Hamiltonian, for both molecular and condensed-phase systems, with PySCFAD, a differentiable QM workflow that facilitates its indirect training against functions of the Hamiltonian, such as electronic energy levels, dipole moments, polarizability, etc. We then use this framework to explore various possible choices within the design space of hybrid ML/QM models, examining the influence of incorporating multiple targets on model performance and learning a reduced-basis ML Hamiltonian that can reproduce targets computed from a much larger basis. Our benchmarks evaluate the accuracy and transferability of these hybrid models, compare them against predictions of atomic properties from their surrogate models, and provide indications to guide the design of the interface between the ML and QM components of the model.
title Exploring the design space of machine-learning models for quantum chemistry with a fully differentiable framework
topic Chemical Physics
url https://arxiv.org/abs/2504.01187