Approximation and Generalization of DeepONets for Learning Operators Arising from a Class of Singularly Perturbed Problems
Year: 2024
Author: Ting Du, Zhongyi Huang, Ye Li
East Asian Journal on Applied Mathematics, Vol. 14 (2024), Iss. 4 : pp. 841–873
Abstract
Singularly perturbed problems present inherent difficulty due to the presence of thin layers in their solutions. To overcome this difficulty, we propose using deep operator networks (DeepONets), a method previously shown to be effective in approximating nonlinear operators between infinite-dimensional Banach spaces. In this paper, we demonstrate for the first time the application of DeepONets to one-dimensional singularly perturbed problems, achieving promising results that suggest their potential as a robust tool for solving this class of problems. We consider the convergence rate of the approximation error incurred by the operator networks in approximating the solution operator, and examine the generalization gap and empirical risk, all of which are shown to converge uniformly with respect to the perturbation parameter. By utilizing Shishkin mesh points as locations of the loss function, we conduct several numerical experiments that provide further support for the effectiveness of operator networks in capturing the singular layer behavior.
You do not have full access to this article.
Already a Subscriber? Sign in as an individual or via your institution
Journal Article Details
Publisher Name: Global Science Press
Language: English
DOI: https://doi.org/10.4208/eajam.2023-128.051023
East Asian Journal on Applied Mathematics, Vol. 14 (2024), Iss. 4 : pp. 841–873
Published online: 2024-01
AMS Subject Headings:
Copyright: COPYRIGHT: © Global Science Press
Pages: 33
Keywords: Deep operator network singularly perturbed problem Shishkin mesh uniform convergence.