Adaptive neural network basis methods for partial differential equations with low-regular solutions

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Huang, Jianguo, Wu, Haohao, Zhou, Tao
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929575054802944
author Huang, Jianguo
Wu, Haohao
Zhou, Tao
author_facet Huang, Jianguo
Wu, Haohao
Zhou, Tao
contents This paper aims to devise an adaptive neural network basis method for numerically solving a second-order semilinear partial differential equation (PDE) with low-regular solutions in two/three dimensions. The method is obtained by combining basis functions from a class of shallow neural networks and the resulting multi-scale analogues, a residual strategy in adaptive methods and the non-overlapping domain decomposition method. At the beginning, in view of the solution residual, we partition the total domain $Ω$ into $K+1$ non-overlapping subdomains, denoted respectively as $\{Ω_k\}_{k=0}^K$, where the exact solution is smooth on subdomain $Ω_{0}$ and low-regular on subdomain $Ω_{k}$ ($1\le k\le K$). Secondly, the low-regular solutions on different subdomains \(Ω_{k}\)~($1\le k\le K$) are approximated by neural networks with different scales, while the smooth solution on subdomain \(Ω_0\) is approximated by the initialized neural network. Thirdly, we determine the undetermined coefficients by solving the linear least squares problems directly or the nonlinear least squares problem via the Gauss-Newton method. The proposed method can be extended to multi-level case naturally. Finally, we use this adaptive method for several peak problems in two/three dimensions to show its high-efficient computational performance.
format Preprint
id arxiv_https___arxiv_org_abs_2411_01998
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Adaptive neural network basis methods for partial differential equations with low-regular solutions
Huang, Jianguo
Wu, Haohao
Zhou, Tao
Numerical Analysis
This paper aims to devise an adaptive neural network basis method for numerically solving a second-order semilinear partial differential equation (PDE) with low-regular solutions in two/three dimensions. The method is obtained by combining basis functions from a class of shallow neural networks and the resulting multi-scale analogues, a residual strategy in adaptive methods and the non-overlapping domain decomposition method. At the beginning, in view of the solution residual, we partition the total domain $Ω$ into $K+1$ non-overlapping subdomains, denoted respectively as $\{Ω_k\}_{k=0}^K$, where the exact solution is smooth on subdomain $Ω_{0}$ and low-regular on subdomain $Ω_{k}$ ($1\le k\le K$). Secondly, the low-regular solutions on different subdomains \(Ω_{k}\)~($1\le k\le K$) are approximated by neural networks with different scales, while the smooth solution on subdomain \(Ω_0\) is approximated by the initialized neural network. Thirdly, we determine the undetermined coefficients by solving the linear least squares problems directly or the nonlinear least squares problem via the Gauss-Newton method. The proposed method can be extended to multi-level case naturally. Finally, we use this adaptive method for several peak problems in two/three dimensions to show its high-efficient computational performance.
title Adaptive neural network basis methods for partial differential equations with low-regular solutions
topic Numerical Analysis
url https://arxiv.org/abs/2411.01998