Multiscale Neural Networks for Approximating Green's Functions

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Hao, Wenrui, Li, Rui Peng, Xi, Yuanzhe, Xu, Tianshi, Yang, Yahong
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911276731465728
author Hao, Wenrui
Li, Rui Peng
Xi, Yuanzhe
Xu, Tianshi
Yang, Yahong
author_facet Hao, Wenrui
Li, Rui Peng
Xi, Yuanzhe
Xu, Tianshi
Yang, Yahong
contents Neural networks (NNs) have been widely used to solve partial differential equations (PDEs) in the applications of physics, biology, and engineering. One effective approach for solving PDEs with a fixed differential operator is learning Green's functions. However, Green's functions are notoriously difficult to learn due to their poor regularity, which typically requires larger NNs and longer training times. In this paper, we address these challenges by leveraging multiscale NNs to learn Green's functions. Through theoretical analysis using multiscale Barron space methods and experimental validation, we show that the multiscale approach significantly reduces the necessary NN size and accelerates training.
format Preprint
id arxiv_https___arxiv_org_abs_2410_18439
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Multiscale Neural Networks for Approximating Green's Functions
Hao, Wenrui
Li, Rui Peng
Xi, Yuanzhe
Xu, Tianshi
Yang, Yahong
Numerical Analysis
65N55, 65N80, 68T07
Neural networks (NNs) have been widely used to solve partial differential equations (PDEs) in the applications of physics, biology, and engineering. One effective approach for solving PDEs with a fixed differential operator is learning Green's functions. However, Green's functions are notoriously difficult to learn due to their poor regularity, which typically requires larger NNs and longer training times. In this paper, we address these challenges by leveraging multiscale NNs to learn Green's functions. Through theoretical analysis using multiscale Barron space methods and experimental validation, we show that the multiscale approach significantly reduces the necessary NN size and accelerates training.
title Multiscale Neural Networks for Approximating Green's Functions
topic Numerical Analysis
65N55, 65N80, 68T07
url https://arxiv.org/abs/2410.18439