English
Related papers

Related papers: Neural network approximation of regularized densit…

200 papers

Recent work has established Moreau-Yosida regularization as a mathematical tool to achieve rigorous functional differentiability in density-functional theory. In this article, we extend this tool to paramagnetic current-density-functional…

Within density-functional theory, Moreau-Yosida regularization enables both a reformulation of the theory and a mathematically well-defined definition of the Kohn-Sham approach. It is further employed in density-potential inversion schemes…

Materials Science · Physics 2026-04-20 Markus Penz , Michael F. Herbst , Trygve Helgaker , Andre Laestadius

Moreau-Yosida regularization is introduced into the framework of exact DFT. Moreau-Yosida regularization is a lossless operation on lower semicontinuous proper convex functions over separable Hilbert spaces, and when applied to the…

Numerical Analysis · Mathematics 2022-08-11 Simen Kvaal

The universal density functional $F$ of density-functional theory is a complicated and ill-behaved function of the density-in particular, $F$ is not differentiable, making many formal manipulations more complicated. Whilst $F$ has been well…

Chemical Physics · Physics 2015-06-18 Simen Kvaal , Ulf Ekström , Andrew M. Teale , Trygve Helgaker

Density-functional theory is a formally exact description of a many-body quantum system in terms of its density; in practice, however, approximations to the universal density functional are required. In this work, a model based on deep…

Computational Physics · Physics 2016-08-02 Jeffrey M. McMahon

For any given neural network architecture a permutation of weights and biases results in the same functional network. This implies that optimization algorithms used to `train' or `learn' the network are faced with a very large number (in…

Optimization and Control · Mathematics 2022-02-22 Harbir Antil , Thomas S. Brown , Rainald Löhner , Fumiya Togashi , Deepanshu Verma

One of the potential applications of a quantum computer is solving quantum chemical systems. It is known that one of the fastest ways to obtain somewhat accurate solutions classically is to use approximations of density functional theory.…

Quantum Physics · Physics 2020-11-18 Thomas E. Baker , David Poulin

Density functional theory (DFT) offers a desirable balance between quantitative accuracy and computational efficiency in practical many-electron calculations. Its central component, the exchange-correlation energy functional, has been…

Universal approximation theorems provide a mathematical explanation for the expressive power of neural networks. They assert that, under mild conditions on the activation function, feedforward neural networks are dense in broad function…

Machine Learning · Computer Science 2026-05-21 Soumendu Sundar Mukherjee , Himasish Talukdar

A detailed convex analysis-based formulation of density-functional theory for periodic systems in arbitrary dimensions is presented. The electron-electron interaction is taken to be of Yukawa type, harmonising with underlying function…

Chemical Physics · Physics 2026-02-23 Oliver M. Bohle , Maryam Lotfigolian , Andre Laestadius , Erik I. Tellgren

We train a neural network as the universal exchange-correlation functional of density-functional theory that simultaneously reproduces both the exact exchange-correlation energy and potential. This functional is extremely non-local, but…

Computational Physics · Physics 2019-10-10 Jonathan Schmidt , Carlos L. Benavides-Riveros , Miguel A. L. Marques

Universal approximation theory offers a foundational framework to verify neural network expressiveness, enabling principled utilization in real-world applications. However, most existing theoretical constructions are established by…

Machine Learning · Computer Science 2026-01-27 ZeYu Li , ShiJun Zhang , TieYong Zeng , FengLei Fan

Deep neural networks (DNNs) have become increasingly important due to their excellent empirical performance on a wide range of problems. However, regularization is generally achieved by indirect means, largely due to the complex set of…

Machine Learning · Computer Science 2018-07-02 Amal Rannen Triki , Maxim Berman , Matthew B. Blaschko

Is there any theoretical guarantee for the approximation ability of neural networks? The answer to this question is the "Universal Approximation Theorem for Neural Networks". This theorem states that a neural network is dense in a certain…

Machine Learning · Computer Science 2021-02-23 Takato Nishijima

Density functional theory underlies the most successful and widely used numerical methods for electronic structure prediction of solids. However, it has the fundamental shortcoming that the universal density functional is unknown. In…

Disordered Systems and Neural Networks · Physics 2020-09-23 M. Michael Denner , Mark H. Fischer , Titus Neupert

The exact Kohn-Sham iteration of generalized density-functional theory in finite dimensions witha Moreau-Yosida regularized universal Lieb functional and an adaptive damping step is shown toconverge to the correct ground-state density.

Chemical Physics · Physics 2020-10-01 Markus Penz , Andre Laestadius , Erik I. Tellgren , Michael Ruggenthaler

For a quantum-mechanical many-electron system, given a density, the Zhao-Morrison-Parr method allows to compute the effective potential that yields precisely that density. In this work, we demonstrate how this and similar inversion…

Chemical Physics · Physics 2023-04-04 Markus Penz , Mihály A. Csirik , Andre Laestadius

The Kohn-Sham iteration of generalized density-functional theory on Banach spaces with Moreau-Yosida regularized universal Lieb functional and an adaptive damping step is shown to converge to the correct ground-state density. This result…

Mathematical Physics · Physics 2025-04-03 Markus Penz , Andre Laestadius

Practical density functional theory (DFT) owes its success to the groundbreaking work of Kohn and Sham that introduced the exact calculation of the non-interacting kinetic energy of the electrons using an auxiliary mean-field system.…

Chemical Physics · Physics 2023-11-17 P. del Mazo-Sevillano , J. Hermann

This paper extends the proof of density of neural networks in the space of continuous (or even measurable) functions on Euclidean spaces to functions on compact sets of probability measures. By doing so the work parallels a more then a…

Machine Learning · Computer Science 2019-06-04 Tomas Pevny , Vojtech Kovarik
‹ Prev 1 2 3 10 Next ›