A Regularity Theory for Static Schrödinger Equations on Rd in Spectral Barron Spaces

DOI10.1137/22M1478719MaRDI QIDQ5887733zbMATH OpenFDO

Authors Ziang Chen, Yulong Lu, Jianfeng Lu

Publication date 13 April 2023

Published in SIAM Journal on Mathematical Analysis (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/2201.10072

zbMATH Keywords

neural networksregularity theorySchrödinger equationbarron space

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) PDEs in connection with quantum mechanics (35Q40) Numerical methods for partial differential equations, boundary value problems (65N99)

Recommendations

• A regularity property for Schrödinger equations on bounded domains
• Regularity properties of Schrödinger equations in vector-valued spaces and applications
• On the Schrödinger equation in \(L^ p\) spaces
• scientific article; zbMATH DE number 3895502
• Besov spaces for the Schrödinger operator with barrier potential
• On the regularity forp-Laplace Schrödinger equations with singular potentials
• Regularity for eigenfunctions of Schrödinger operators
• On the regularity of the semilinear term on the Cauchy problem for the Schrödinger equation
• Regularity for inhomogeneous Dirichlet problems of some Schrödinger equations on domains
• On the regularity of the electronic Schrödinger equation in Hilbert spaces of mixed derivatives

Cites work

• scientific article; zbMATH DE number 5870071 (Why is no real title available?)
• scientific article; zbMATH DE number 1324223 (Why is no real title available?)
• A priori generalization error analysis of two-layer neural networks for solving high dimensional Schrödinger eigenvalue problems
• Algorithms for solving high dimensional PDEs: from nonlinear Monte Carlo to machine learning
• Banach space representer theorems for neural networks and ridge splines
• Breaking the curse of dimensionality with convex neural networks
• Deep learning-based numerical methods for high-dimensional parabolic partial differential equations and backward stochastic differential equations
• High-order approximation rates for shallow neural networks with cosine and \(\mathrm{ReLU}^k\) activation functions
• Solving high-dimensional partial differential equations using deep learning
• The Kolmogorov-Riesz compactness theorem
• The deep Ritz method: a deep learning-based numerical algorithm for solving variational problems
• Universal approximation bounds for superpositions of a sigmoidal function

Cited in

(4)

• Deep learning methods for partial differential equations and related parameter identification problems
• Improved Analysis of PINNs: Alleviate the CoD for Compositional Solutions
• Numerical analysis of physics-informed neural networks and related models in physics-informed machine learning
• A Regularity Theory for Static Schr\"odinger Equations on $\mathbb{R}^d$ in Spectral Barron Spaces

This page was built for publication: A Regularity Theory for Static Schrödinger Equations on \(\boldsymbol{\mathbb{R}}\)^d in Spectral Barron Spaces

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5887733)