Orbital-Free Surrogate Functionals Yield Transferable Interatomic Potentials and Electron Densities
Abstract
Orbital-free density functional theory seeks to compute the energy of an electronic system directly from its electron density, avoiding one-electron wave functions and thereby offering a route to scalable electronic structure calculations. Machine-learned orbital-free density functionals have recently achieved promising results on small organic molecules, predicting energies with sub-millihartree accuracy. However, their convergence in density optimization remains sensitive to hyperparameter tuning and architectural choices. Here, we extend the recently introduced (weak) surrogate functional framework - designed to predict ground-state electron densities only - to also yield their energy, resulting in "strong" surrogate functionals. We find that these learned functionals enable stable convergence across all tested neural network backbones, reducing electron density errors relative to the Kohn-Sham reference by an order of magnitude compared to previous OF-DFT methods. More importantly, the predicted energies are competitive with state-of-the-art machine-learned interatomic potentials (MLIPs) trained only on energies, while exhibiting superior generalization to larger, unseen systems.
Related
- Correcting the Liquid Densities of Universal Machine-Learning Interatomic Potentials Using Local-Number-Density Repulsion
- Accurate, transferable, and verifiable machine-learned interatomic potentials for layered materials
- Predicting Thermophysical Properties of Halide Salts Using On-the-Fly Machine-Learned Interatomic Potentials Across Multiple Exchange-Correlation Functionals
- Stationarity Constraints Improve Both Energies and Densities of Machine-Learned Exchange-Correlation Functionals
- Transformer-inspired architectures make machine-learned electron densities accurate and transferable enough to bypass self-consistency
BibTeX
@misc{wagner2026orbitalfree,
title = {{Orbital-Free Surrogate Functionals Yield Transferable Interatomic Potentials and Electron Densities}},
author = {Simon Wagner and Marc K. Ickler and Manuel V. Klockow and Fred A. Hamprecht and Roman Remme},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.21882},
eprint = {2609.21882},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.21882},
}
RIS
TY - UNPB
TI - Orbital-Free Surrogate Functionals Yield Transferable Interatomic Potentials and Electron Densities
AU - Simon Wagner
AU - Marc K. Ickler
AU - Manuel V. Klockow
AU - Fred A. Hamprecht
AU - Roman Remme
PY - 2026
DA - 2026/09/18
PB - arXiv
DO - 10.48550/arxiv.2609.21882
UR - https://arxiv.org/abs/2609.21882
AB - Orbital-free density functional theory seeks to compute the energy of an electronic system directly from its electron density, avoiding one-electron wave functions and thereby offering a route to scalable electronic structure calculations. Machine-learned orbital-free density functionals have recently achieved promising results on small organic molecules, predicting energies with sub-millihartree accuracy. However, their convergence in density optimization remains sensitive to hyperparameter tuning and architectural choices. Here, we extend the recently introduced (weak) surrogate functional framework - designed to predict ground-state electron densities only - to also yield their energy, resulting in "strong" surrogate functionals. We find that these learned functionals enable stable convergence across all tested neural network backbones, reducing electron density errors relative to the Kohn-Sham reference by an order of magnitude compared to previous OF-DFT methods. More importantly, the predicted energies are competitive with state-of-the-art machine-learned interatomic potentials (MLIPs) trained only on energies, while exhibiting superior generalization to larger, unseen systems.
ER -