Machine learning the derivative discontinuity of density-functional theory

Abstract

Machine learning is a powerful tool to design accurate, highly non-local, exchange-correlation functionals for density functional theory. So far, most of those machine learned functionals are trained for systems with an integer number of particles. As such, they are unable to reproduce some crucial and fundamental aspects, such as the explicit dependency of the functionals on the particle number or the infamous derivative discontinuity at integer particle numbers. Here we propose a solution to these problems by training a neural network as the universal functional of density-functional theory that (i) depends explicitly on the number of particles with a piece-wise linearity between the integer numbers and (ii) reproduces the derivative discontinuity of the exchange-correlation energy. This is achieved by using an ensemble formalism, a training set containing fractional densities, and an explicitly discontinuous formulation.

References in corpus (9)

• Localization and delocalization errors in density functional theory and implications for band-gap prediction
• An approximation to density functional theory for an accurate calculation of band-gaps of semiconductors
• Piecewise Linearity of Approximate Density Functionals Revisited: Implications for Frontier Orbital Energies
• Towards a formal definition of static and dynamic electronic correlations
• Derivative discontinuity and exchange-correlation potential of meta-GGAs in density-functional theory
• On derivatives of the energy with respect to total electron number and orbital occupation numbers. A critique of Janak's theorem
• Machine Learning Universal Bosonic Functionals
• Chemistry in One Dimension
• Efficient Learning of a One-dimensional Density Functional Theory

Cited by in corpus (15)

• Why neural functionals suit statistical mechanics
• Hyper-density functional theory of soft matter
• Neural density functionals: Local learning and pair-correlation matching
• Neural density functional theory of liquid-gas phase coexistence
• Artificial Intelligence for Science in Quantum, Atomistic, and Continuum Systems
• Why hyperdensity functionals describe any equilibrium observable
• Neural Quantum Propagators for Driven-Dissipative Quantum Dynamics
• Machine learning for accuracy in density functional approximations
• The tilted-plane structure of the energy of finite quantum systems
• Inverting the Kohn-Sham equations with physics-informed machine learning
• Orbital-Free Quasi-Density Functional Theory
• Predicting fermionic densities using a Projected Quantum Kernel method
• Homogeneous Electron Liquid in Arbitrary Dimensions: Exchange and Correlation Using the Singwi-Tosi-Land-Sjölander Approach
• Excitations of Quantum Many-Body Systems via Purified Ensembles: A Unitary-Coupled-Cluster-based Approach
• Toward Density Functional Theory on Quantum Computers?