Newton Informed Neural Operator for Computing Multiple Solutions of Nonlinear Partials Differential Equations

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Hao, Wenrui, Liu, Xinliang, Yang, Yahong
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910457665683456
author Hao, Wenrui
Liu, Xinliang
Yang, Yahong
author_facet Hao, Wenrui
Liu, Xinliang
Yang, Yahong
contents Solving nonlinear partial differential equations (PDEs) with multiple solutions using neural networks has found widespread applications in various fields such as physics, biology, and engineering. However, classical neural network methods for solving nonlinear PDEs, such as Physics-Informed Neural Networks (PINN), Deep Ritz methods, and DeepONet, often encounter challenges when confronted with the presence of multiple solutions inherent in the nonlinear problem. These methods may encounter ill-posedness issues. In this paper, we propose a novel approach called the Newton Informed Neural Operator, which builds upon existing neural network techniques to tackle nonlinearities. Our method combines classical Newton methods, addressing well-posed problems, and efficiently learns multiple solutions in a single learning process while requiring fewer supervised data points compared to existing neural network methods.
format Preprint
id arxiv_https___arxiv_org_abs_2405_14096
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Newton Informed Neural Operator for Computing Multiple Solutions of Nonlinear Partials Differential Equations
Hao, Wenrui
Liu, Xinliang
Yang, Yahong
Machine Learning
Numerical Analysis
Solving nonlinear partial differential equations (PDEs) with multiple solutions using neural networks has found widespread applications in various fields such as physics, biology, and engineering. However, classical neural network methods for solving nonlinear PDEs, such as Physics-Informed Neural Networks (PINN), Deep Ritz methods, and DeepONet, often encounter challenges when confronted with the presence of multiple solutions inherent in the nonlinear problem. These methods may encounter ill-posedness issues. In this paper, we propose a novel approach called the Newton Informed Neural Operator, which builds upon existing neural network techniques to tackle nonlinearities. Our method combines classical Newton methods, addressing well-posed problems, and efficiently learns multiple solutions in a single learning process while requiring fewer supervised data points compared to existing neural network methods.
title Newton Informed Neural Operator for Computing Multiple Solutions of Nonlinear Partials Differential Equations
topic Machine Learning
Numerical Analysis
url https://arxiv.org/abs/2405.14096