Journals
Resources
About Us
Open Access

Deep Ritz Methods for Laplace Equations with Dirichlet Boundary Condition

Deep Ritz Methods for Laplace Equations with Dirichlet Boundary Condition

Year:    2022

Author:    Chenguang Duan, Yuling Jiao, Yanming Lai, Xiliang Lu, Qimeng Quan, Jerry Zhijian Yang

CSIAM Transactions on Applied Mathematics, Vol. 3 (2022), Iss. 4 : pp. 761–791

Abstract

Deep Ritz methods (DRM) have been proven numerically to be efficient in solving partial differential equations. In this paper, we present a convergence rate in $H^1$ norm for deep Ritz methods for Laplace equations with Dirichlet boundary condition, where the error depends on the depth and width in the deep neural networks and the number of samples explicitly. Further we can properly choose the depth and width in the deep neural networks in terms of the number of training samples. The main idea of the proof is to decompose the total error of DRM into three parts, that is approximation error, statistical error and the error caused by the boundary penalty. We bound the approximation error in $H^1$ norm with ${\rm ReLU}^2$ networks and control the statistical error via Rademacher complexity. In particular, we derive the bound on the Rademacher complexity of the non-Lipschitz composition of gradient norm with ${\rm ReLU}^2$ network, which is of immense independent interest. We also analyze the error inducing by the boundary penalty method and give a prior rule for tuning the penalty parameter.

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/csiam-am.SO-2021-0043

CSIAM Transactions on Applied Mathematics, Vol. 3 (2022), Iss. 4 : pp. 761–791

Published online:    2022-01

AMS Subject Headings:    Global Science Press

Copyright:    COPYRIGHT: © Global Science Press

Pages:    31

Keywords:    Deep Ritz methods convergence rate Dirichlet boundary condition approximation error Rademacher complexity.

Author Details

Chenguang Duan

Yuling Jiao

Yanming Lai

Xiliang Lu

Qimeng Quan

Jerry Zhijian Yang

  1. Erratum to “A priori and a posteriori error estimates for the Deep Ritz method applied to the Laplace and Stokes problem” [J. Comput. Appl. Math. 421 (2023) 114845 ]

    Minakowski, P. | Richter, T.

    Journal of Computational and Applied Mathematics, Vol. 460 (2025), Iss. P.116406

    https://doi.org/10.1016/j.cam.2024.116406 [Citations: 0]
  2. Solving Elliptic Problems with Singular Sources Using Singularity Splitting Deep Ritz Method

    Hu, Tianhao | Jin, Bangti | Zhou, Zhi

    SIAM Journal on Scientific Computing, Vol. 45 (2023), Iss. 4 P.A2043

    https://doi.org/10.1137/22M1520840 [Citations: 2]