Saved in:
Bibliographic Details
Main Authors: Matsubara, Takashi, Yaguchi, Takaharu
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2307.13869
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929622228140032
author Matsubara, Takashi
Yaguchi, Takaharu
author_facet Matsubara, Takashi
Yaguchi, Takaharu
contents Physics-informed neural networks solve partial differential equations by training neural networks. Since this method approximates infinite-dimensional PDE solutions with finite collocation points, minimizing discretization errors by selecting suitable points is essential for accelerating the learning process. Inspired by number theoretic methods for numerical analysis, we introduce good lattice training and periodization tricks, which ensure the conditions required by the theory. Our experiments demonstrate that GLT requires 2-7 times fewer collocation points, resulting in lower computational cost, while achieving competitive performance compared to typical sampling methods.
format Preprint
id arxiv_https___arxiv_org_abs_2307_13869
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Number Theoretic Accelerated Learning of Physics-Informed Neural Networks
Matsubara, Takashi
Yaguchi, Takaharu
Machine Learning
Numerical Analysis
Physics-informed neural networks solve partial differential equations by training neural networks. Since this method approximates infinite-dimensional PDE solutions with finite collocation points, minimizing discretization errors by selecting suitable points is essential for accelerating the learning process. Inspired by number theoretic methods for numerical analysis, we introduce good lattice training and periodization tricks, which ensure the conditions required by the theory. Our experiments demonstrate that GLT requires 2-7 times fewer collocation points, resulting in lower computational cost, while achieving competitive performance compared to typical sampling methods.
title Number Theoretic Accelerated Learning of Physics-Informed Neural Networks
topic Machine Learning
Numerical Analysis
url https://arxiv.org/abs/2307.13869