An analysis of the derivative-free loss method for solving PDEs

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Han, Jihun, Lee, Yoonsang
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909848558370816
author Han, Jihun
Lee, Yoonsang
author_facet Han, Jihun
Lee, Yoonsang
contents This study analyzes the derivative-free loss method to solve a certain class of elliptic PDEs and fluid problems using neural networks. The approach leverages the Feynman-Kac formulation, incorporating stochastic walkers and their averaged values. We investigate how the time interval associated with the Feynman-Kac representation and the walker size influence computational efficiency, trainability, and sampling errors. Our analysis shows that the training loss bias scales proportionally with the time interval and the spatial gradient of the neural network, while being inversely proportional to the walker size. Moreover, we demonstrate that the time interval must be sufficiently long to enable effective training. These results indicate that the walker size can be chosen as small as possible, provided it satisfies the optimal lower bound determined by the time interval. Finally, we present numerical experiments that support our theoretical findings.
format Preprint
id arxiv_https___arxiv_org_abs_2309_16829
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle An analysis of the derivative-free loss method for solving PDEs
Han, Jihun
Lee, Yoonsang
Numerical Analysis
Machine Learning
65N15, 65N75, 65C05, 60G46
This study analyzes the derivative-free loss method to solve a certain class of elliptic PDEs and fluid problems using neural networks. The approach leverages the Feynman-Kac formulation, incorporating stochastic walkers and their averaged values. We investigate how the time interval associated with the Feynman-Kac representation and the walker size influence computational efficiency, trainability, and sampling errors. Our analysis shows that the training loss bias scales proportionally with the time interval and the spatial gradient of the neural network, while being inversely proportional to the walker size. Moreover, we demonstrate that the time interval must be sufficiently long to enable effective training. These results indicate that the walker size can be chosen as small as possible, provided it satisfies the optimal lower bound determined by the time interval. Finally, we present numerical experiments that support our theoretical findings.
title An analysis of the derivative-free loss method for solving PDEs
topic Numerical Analysis
Machine Learning
65N15, 65N75, 65C05, 60G46
url https://arxiv.org/abs/2309.16829