Bridging electronic and classical density-functional theory using universal machine-learned functional approximations

Abstract

The accuracy of density-functional theory (DFT) is determined by the quality of the approximate functionals, such as exchange-correlation in electronic DFT and the excess functional in the classical DFT formalism of fluids. The exact functional is highly nonlocal for both electrons and fluids, yet most approximate functionals are semi-local or nonlocal in a limited weighted-density form. Machine-learned (ML) nonlocal density-functional approximations are promising in both electronic and classical DFT, but have so far employed disparate approaches with limited generality. Here, we formulate a universal approximation framework and training protocol for nonlocal ML functionals, combining features of equivariant convolutional neural networks and the weighted-density approximation. We prototype this approach for several 1D and quasi-1D problems and demonstrate that a functional with exactly the same hyperparameters achieves excellent accuracy for the hard-rod fluid, the inhomogeneous Ising model, the exact exchange functional for electrons, the electron kinetic energy functional for orbital-free DFT, as well as for liquid water with 1D inhomogeneities. These results lay the foundation for a universal ML approach to exact 3D functionals spanning electronic and classical DFT.

12 pages, 7 figures

References in corpus (17)

• Perspective on density functional theory
• By-passing the Kohn-Sham equations with machine learning
• Finding Density Functionals with Machine Learning
• A Transferable Machine-Learning Model of the Electron Density
• Deep-Learning Density Functional Theory Hamiltonian for Efficient ab initio Electronic-Structure Calculation
• General framework for E(3)-equivariant neural network representation of density functional theory Hamiltonian
• Joint density-functional theory for electronic structure of solvated systems
• Density functional theory beyond the linear regime: Validating adiabatic LDA
• Equivariant representations for molecular Hamiltonians and N-center atomic-scale properties
• Neural functional theory for inhomogeneous fluids: Fundamentals and applications
• Efficient classical density-functional theories of rigid-molecular fluids and a simplified free energy functional for liquid water
• Universal Machine Learning Kohn-Sham Hamiltonian for Materials
• A computationally efficacious free-energy functional for studies of inhomogeneous liquid water
• A recipe for free-energy functionals of polarizable molecular fluids
• Why neural functionals suit statistical mechanics
• Nonlocal Machine-Learned Exchange Functional for Molecules and Solids
• Variational principle to regularize machine-learned density functionals: the non-interacting kinetic-energy functional

Cited by in corpus (10)

• Neural density functional theory of liquid-gas phase coexistence
• A Snapshot of Time-Dependent Density-Functional Theory
• Why hyperdensity functionals describe any equilibrium observable
• Metadensity functional theory for classical fluids: Extracting the pair potential
• Learning the bulk and interfacial physics of liquid-liquid phase separation with neural density functionals
• Neural Density Functional Theory in Higher Dimensions with Convolutional Layers
• Gauge invariance and hyperforce correlation theory for equilibrium fluid mixtures
• Determining the chemical potential via universal density functional learning
• Metadensity functional learning for classical fluids: Regularizing with pair correlations
• eminus -- Pythonic electronic structure theory