Loading [MathJax]/jax/output/CommonHTML/jax.js
Journals
Resources
About Us
Open Access
Go to previous page

A Rate of Convergence of Physics Informed Neural Networks for the Linear Second Order Elliptic PDEs

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

  1. Solving Poisson Problems in Polygonal Domains with Singularity Enriched Physics Informed Neural Networks

    Hu, Tianhao | Jin, Bangti | Zhou, Zhi

    SIAM Journal on Scientific Computing, Vol. 46 (2024), Iss. 4 P.C369

    https://doi.org/10.1137/23M1601195 [Citations: 2]
  2. Generalization of PINNs for elliptic interface problems

    Jiang, Xuelian | Wang, Ziming | Bao, Wei | Xu, Yingxiang

    Applied Mathematics Letters, Vol. 157 (2024), Iss. P.109175

    https://doi.org/10.1016/j.aml.2024.109175 [Citations: 0]
  3. Solving PDEs on spheres with physics-informed convolutional neural networks

    Lei, Guanhang | Lei, Zhen | Shi, Lei | Zeng, Chenyu | Zhou, Ding-Xuan

    Applied and Computational Harmonic Analysis, Vol. 74 (2025), Iss. P.101714

    https://doi.org/10.1016/j.acha.2024.101714 [Citations: 0]
  4. Current density impedance imaging with PINNs

    Duan, Chenguang | Huang, Junjun | Jiao, Yuling | Lu, Xiliang | Yang, Jerry Zhijian

    Journal of Computational and Applied Mathematics, Vol. 452 (2024), Iss. P.116120

    https://doi.org/10.1016/j.cam.2024.116120 [Citations: 0]
  5. Energy dissipation preserving physics informed neural network for Allen-Cahn equations

    Kütük, Mustafa | Yücel, Hamdullah

    Journal of Computational Science, Vol. (2025), Iss. P.102577

    https://doi.org/10.1016/j.jocs.2025.102577 [Citations: 0]
  6. Novel and general discontinuity-removing PINNs for elliptic interface problems

    Fan, Haolong | Tan, Zhijun

    Journal of Computational Physics, Vol. 529 (2025), Iss. P.113861

    https://doi.org/10.1016/j.jcp.2025.113861 [Citations: 0]
  7. Convergence analysis of deep Ritz method with over-parameterization

    Ding, Zhao | Jiao, Yuling | Lu, Xiliang | Wu, Peiying | Yang, Jerry Zhijian

    Neural Networks, Vol. 184 (2025), Iss. P.107110

    https://doi.org/10.1016/j.neunet.2024.107110 [Citations: 0]
  8. An Accurate and Efficient Continuity-Preserved Method Based on Randomized Neural Networks for Elliptic Interface Problems

    Ying, Jinyong | Hu, Jingying | Shi, Zuoshunhua | Li, Jiao

    SIAM Journal on Scientific Computing, Vol. 46 (2024), Iss. 5 P.C633

    https://doi.org/10.1137/24M1632309 [Citations: 0]
  9. 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, Yunfei

    2023

    https://doi.org/10.1007/978-3-031-37800-3_4 [Citations: 1]
  10. An iterative deep Ritz method for monotone elliptic problems

    Hu, Tianhao | Jin, Bangti | Wang, Fengru

    Journal of Computational Physics, Vol. 527 (2025), Iss. P.113791

    https://doi.org/10.1016/j.jcp.2025.113791 [Citations: 0]
  11. ERROR ESTIMATES OF RESIDUAL MINIMIZATION USING NEURAL NETWORKS FOR LINEAR PDES

    Shin, Yeonjong | Zhang, Zhongqiang | Karniadakis, George Em

    Journal of Machine Learning for Modeling and Computing, Vol. 4 (2023), Iss. 4 P.73

    https://doi.org/10.1615/JMachLearnModelComput.2023050411 [Citations: 21]
  12. 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]