Numerical solution of Poisson partial differential equations in high dimension using two-layer neural networks
Numerical Analysis
2023-07-14 v2 Numerical Analysis
Analysis of PDEs
Optimization and Control
Abstract
The aim of this article is to analyze numerical schemes using two-layer neural networks with infinite width for the resolution of the high-dimensional Poisson-Neumann partial differential equations (PDEs) with Neumann boundary conditions. Using Barron's representation of the solution with a measure of probability, the energy is minimized thanks to a gradient curve dynamic on the Wasserstein space of parameters defining the neural network. Inspired by the work from Bach and Chizat, we prove that if the gradient curve converges, then the represented function is the solution of the elliptic equation considered. Numerical experiments are given to show the potential of the method.
Cite
@article{arxiv.2305.09408,
title = {Numerical solution of Poisson partial differential equations in high dimension using two-layer neural networks},
author = {Mathias Dus and Virginie Ehrlacher},
journal= {arXiv preprint arXiv:2305.09408},
year = {2023}
}