A Rate of Convergence of Physics Informed Neural Networks for the Linear Second Order Elliptic PDEs
Year: 2022
Author: Yuling Jiao, Yanming Lai, Dingwei Li, Xiliang Lu, Fengru Wang, Yang Wang, Jerry Zhijian Yang
Communications in Computational Physics, Vol. 31 (2022), Iss. 4 : pp. 1272–1295
Abstract
In recent years, physical informed neural networks (PINNs) have been shown to be a powerful tool for solving PDEs empirically. However, numerical analysis of PINNs is still missing. In this paper, we prove the convergence rate to PINNs for the second order elliptic equations with Dirichlet boundary condition, by establishing the upper bounds on the number of training samples, depth and width of the deep neural networks to achieve desired accuracy. The error of PINNs is decomposed into approximation error and statistical error, where the approximation error is given in C2 norm with ReLU3 networks (deep network with activation function max{0,x3}) and the statistical error is estimated by Rademacher complexity. We derive the bound on the Rademacher complexity of the non-Lipschitz composition of gradient norm with ReLU3 network, which is of immense independent interest.
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/cicp.OA-2021-0186
Communications in Computational Physics, Vol. 31 (2022), Iss. 4 : pp. 1272–1295
Published online: 2022-01
AMS Subject Headings: Global Science Press
Copyright: COPYRIGHT: © Global Science Press
Pages: 24
Keywords: PINNs ReLU3 neural network B-splines Rademacher complexity
Author Details
Yuling Jiao Email
Yanming Lai Email
Dingwei Li Email
Xiliang Lu Email
Fengru Wang Email
Yang Wang Email
Jerry Zhijian Yang Email
-
Solving Poisson Problems in Polygonal Domains with Singularity Enriched Physics Informed Neural Networks
Hu, Tianhao | Jin, Bangti | Zhou, ZhiSIAM Journal on Scientific Computing, Vol. 46 (2024), Iss. 4 P.C369
https://doi.org/10.1137/23M1601195 [Citations: 2] -
Generalization of PINNs for elliptic interface problems
Jiang, Xuelian | Wang, Ziming | Bao, Wei | Xu, YingxiangApplied Mathematics Letters, Vol. 157 (2024), Iss. P.109175
https://doi.org/10.1016/j.aml.2024.109175 [Citations: 0] -
Solving PDEs on spheres with physics-informed convolutional neural networks
Lei, Guanhang | Lei, Zhen | Shi, Lei | Zeng, Chenyu | Zhou, Ding-XuanApplied and Computational Harmonic Analysis, Vol. 74 (2025), Iss. P.101714
https://doi.org/10.1016/j.acha.2024.101714 [Citations: 0] -
Current density impedance imaging with PINNs
Duan, Chenguang | Huang, Junjun | Jiao, Yuling | Lu, Xiliang | Yang, Jerry ZhijianJournal of Computational and Applied Mathematics, Vol. 452 (2024), Iss. P.116120
https://doi.org/10.1016/j.cam.2024.116120 [Citations: 0] -
Energy dissipation preserving physics informed neural network for Allen-Cahn equations
Kütük, Mustafa | Yücel, HamdullahJournal of Computational Science, Vol. (2025), Iss. P.102577
https://doi.org/10.1016/j.jocs.2025.102577 [Citations: 0] -
Novel and general discontinuity-removing PINNs for elliptic interface problems
Fan, Haolong | Tan, ZhijunJournal of Computational Physics, Vol. 529 (2025), Iss. P.113861
https://doi.org/10.1016/j.jcp.2025.113861 [Citations: 0] -
Convergence analysis of deep Ritz method with over-parameterization
Ding, Zhao | Jiao, Yuling | Lu, Xiliang | Wu, Peiying | Yang, Jerry ZhijianNeural Networks, Vol. 184 (2025), Iss. P.107110
https://doi.org/10.1016/j.neunet.2024.107110 [Citations: 0] -
An Accurate and Efficient Continuity-Preserved Method Based on Randomized Neural Networks for Elliptic Interface Problems
Ying, Jinyong | Hu, Jingying | Shi, Zuoshunhua | Li, JiaoSIAM Journal on Scientific Computing, Vol. 46 (2024), Iss. 5 P.C633
https://doi.org/10.1137/24M1632309 [Citations: 0] -
From Classical Analysis to Analysis on Fractals
Convergence Analysis of the Deep Galerkin Method for Weak Solutions
Jiao, Yuling | Lai, Yanming | Wang, Yang | Yang, Haizhao | Yang, Yunfei2023
https://doi.org/10.1007/978-3-031-37800-3_4 [Citations: 1] -
An iterative deep Ritz method for monotone elliptic problems
Hu, Tianhao | Jin, Bangti | Wang, FengruJournal of Computational Physics, Vol. 527 (2025), Iss. P.113791
https://doi.org/10.1016/j.jcp.2025.113791 [Citations: 0] -
ERROR ESTIMATES OF RESIDUAL MINIMIZATION USING NEURAL NETWORKS FOR LINEAR PDES
Shin, Yeonjong | Zhang, Zhongqiang | Karniadakis, George EmJournal of Machine Learning for Modeling and Computing, Vol. 4 (2023), Iss. 4 P.73
https://doi.org/10.1615/JMachLearnModelComput.2023050411 [Citations: 21] -
Error convergence and engineering-guided hyperparameter search of PINNs: Towards optimized I-FENN performance
Pantidis, Panos | Eldababy, Habiba | Tagle, Christopher Miguel | Mobasher, Mostafa E.Computer Methods in Applied Mechanics and Engineering, Vol. 414 (2023), Iss. P.116160
https://doi.org/10.1016/j.cma.2023.116160 [Citations: 12]