On the Representation of Solutions to Elliptic PDEs in Barron Spaces

06/14/2021
by   Ziang Chen, et al.
0

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 ϵ-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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/21/2022

Neural Network Approximations of PDEs Beyond Linearity: Representational Perspective

A burgeoning line of research has developed deep neural networks capable...
research
01/05/2021

A Priori Generalization Analysis of the Deep Ritz Method for Solving High Dimensional Elliptic Equations

This paper concerns the a priori generalization analysis of the Deep Rit...
research
10/13/2021

Machine Learning For Elliptic PDEs: Fast Rate Generalization Bound, Neural Scaling Law and Minimax Optimality

In this paper, we study the statistical limits of deep learning techniqu...
research
01/28/2023

Deep Operator Learning Lessens the Curse of Dimensionality for PDEs

Deep neural networks (DNNs) have seen tremendous success in many fields ...
research
12/08/2016

An Efficient Algorithm for the Piecewise-Smooth Model with Approximately Explicit Solutions

This paper presents an efficient approach to image segmentation that app...
research
03/03/2021

Parametric Complexity Bounds for Approximating PDEs with Neural Networks

Recent empirical results show that deep networks can approximate solutio...
research
12/05/2019

Towards identification of explicit solutions to overdetermined systems of differential equations

The authors proposed a general way to find particular solutions for over...

Please sign up or login with your details

Forgot password? Click here to reset