On the Representation of Solutions to Elliptic PDEs in Barron Spaces

Abstract

Numerical solutions to high-dimensional partial differential equations (PDEs) based on neural networks have seen exciting developments. This paper derives complexity estimates of the solutions of $d$-dimensional second-order elliptic PDEs in the Barron space, that is a set of functions admitting the integral of certain parametric ridge function against a probability measure on the parameters. We prove under some appropriate assumptions that if the coefficients and the source term of the elliptic PDE lie in Barron spaces, then the solution of the PDE is $\epsilon$-close with respect to the $H^1$ norm to a Barron function. Moreover, we prove dimension-explicit bounds for the Barron norm of this approximate solution, depending at most polynomially on the dimension $d$ of the PDE. As a direct consequence of the complexity estimates, the solution of the PDE can be approximated on any bounded domain by a two-layer neural network with respect to the $H^1$ norm with a dimension-explicit convergence rate.

arXiv commentaccepted by NeurIPS 2021

References in corpus (16)

• Neural Message Passing for Quantum Chemistry
• DGM: A deep learning algorithm for solving partial differential equations
• Solving the Quantum Many-Body Problem with Artificial Neural Networks
• Solving high-dimensional partial differential equations using deep learning
• Fourier Neural Operator for Parametric Partial Differential Equations
• A Machine Learning Framework for Solving High-Dimensional Mean Field Game and Mean Field Control Problems
• A proof that artificial neural networks overcome the curse of dimensionality in the numerical approximation of Black-Scholes partial differential equations
• SelectNet: Self-paced Learning for High-dimensional Partial Differential Equations
• Two-Layer Neural Networks for Partial Differential Equations: Optimization and Generalization Theory
• Error estimates of residual minimization using neural networks for linear PDEs
• Estimates on the generalization error of Physics Informed Neural Networks (PINNs) for approximating PDEs
• A Priori Generalization Analysis of the Deep Ritz Method for Solving High Dimensional Elliptic Equations
• Some observations on high-dimensional partial differential equations with Barron data
• A Priori Analysis of Stable Neural Network Solutions to Numerical PDEs
• Sharp Representation Theorems for ReLU Networks with Precise Dependence on Depth
• Parametric Complexity Bounds for Approximating PDEs with Neural Networks

Cited by in corpus (3)

• Deep Learning Methods for Partial Differential Equations and Related Parameter Identification Problems
• Embedding Inequalities for Barron-type Spaces
• Stationary Density Estimation of Itô Diffusions Using Deep Learning