A novel number-theoretic sampling method for neural network solutions of partial differential equations

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yang, Yu, He, Pingan, Peng, Xiaoling, He, Qiaolin
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918079709052928
author Yang, Yu
He, Pingan
Peng, Xiaoling
He, Qiaolin
author_facet Yang, Yu
He, Pingan
Peng, Xiaoling
He, Qiaolin
contents Traditional Monte Carlo integration using uniform random sampling exhibits degraded efficiency in low-regularity or high-dimensional problems. We propose a novel deep learning framework based on deterministic number-theoretic sampling points, which is a robust approach specifically designed to handle partial differential equations with rough solutions or in high dimensions. The sample points are generated by the generating vector to achieve the smallest discrepancy. The architecture integrates Physics-Informed Neural Networks (PINNs) with rigorous mathematical guarantees demonstrating lower error bounds compared to conventional uniform random sampling. Numerical validation includes low-regularity Poisson equations, two-dimensional inverse Helmholtz problems, and high-dimensional linear/nonlinear PDEs, systematically demonstrating the algorithm's superior performance and generalization capabilities.
format Preprint
id arxiv_https___arxiv_org_abs_2411_17039
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A novel number-theoretic sampling method for neural network solutions of partial differential equations
Yang, Yu
He, Pingan
Peng, Xiaoling
He, Qiaolin
Numerical Analysis
Traditional Monte Carlo integration using uniform random sampling exhibits degraded efficiency in low-regularity or high-dimensional problems. We propose a novel deep learning framework based on deterministic number-theoretic sampling points, which is a robust approach specifically designed to handle partial differential equations with rough solutions or in high dimensions. The sample points are generated by the generating vector to achieve the smallest discrepancy. The architecture integrates Physics-Informed Neural Networks (PINNs) with rigorous mathematical guarantees demonstrating lower error bounds compared to conventional uniform random sampling. Numerical validation includes low-regularity Poisson equations, two-dimensional inverse Helmholtz problems, and high-dimensional linear/nonlinear PDEs, systematically demonstrating the algorithm's superior performance and generalization capabilities.
title A novel number-theoretic sampling method for neural network solutions of partial differential equations
topic Numerical Analysis
url https://arxiv.org/abs/2411.17039