Loading [MathJax]/jax/output/HTML-CSS/config.js
arrow
Volume 18, Issue 2
Error Analysis of the Deep Mixed Residual Method for High-Order Elliptic Equations

Mengjia Bai, Jingrun Chen, Rui Du & Zhiwei Sun

Numer. Math. Theor. Meth. Appl., 18 (2025), pp. 395-436.

Published online: 2025-05

Export citation
  • Abstract

This paper presents an a priori error analysis of the Deep Mixed Residual method (MIM) for solving high-order elliptic equations with non-homogeneous boundary conditions, including Dirichlet, Neumann, and Robin conditions. We examine MIM with two types of loss functions, referred to as first-order and second-order least squares systems. By providing boundedness and coercivity analysis, we leverage Céa’s Lemma to decompose the total error into the approximation, generalization, and optimization errors. Utilizing the Barron space theory and Rademacher complexity, an a priori error is derived regarding the training samples and network size that are exempt from the curse of dimensionality. Our results reveal that MIM significantly reduces the regularity requirements for activation functions compared to the deep Ritz method, implying the effectiveness of MIM in solving high-order equations.

  • AMS Subject Headings

65N15, 68Q25

  • Copyright

COPYRIGHT: © Global Science Press

  • Email address
  • BibTex
  • RIS
  • TXT
@Article{NMTMA-18-395, author = {Bai , MengjiaChen , JingrunDu , Rui and Sun , Zhiwei}, title = {Error Analysis of the Deep Mixed Residual Method for High-Order Elliptic Equations}, journal = {Numerical Mathematics: Theory, Methods and Applications}, year = {2025}, volume = {18}, number = {2}, pages = {395--436}, abstract = {

This paper presents an a priori error analysis of the Deep Mixed Residual method (MIM) for solving high-order elliptic equations with non-homogeneous boundary conditions, including Dirichlet, Neumann, and Robin conditions. We examine MIM with two types of loss functions, referred to as first-order and second-order least squares systems. By providing boundedness and coercivity analysis, we leverage Céa’s Lemma to decompose the total error into the approximation, generalization, and optimization errors. Utilizing the Barron space theory and Rademacher complexity, an a priori error is derived regarding the training samples and network size that are exempt from the curse of dimensionality. Our results reveal that MIM significantly reduces the regularity requirements for activation functions compared to the deep Ritz method, implying the effectiveness of MIM in solving high-order equations.

}, issn = {2079-7338}, doi = {https://doi.org/10.4208/nmtma.OA-2024-0134}, url = {http://global-sci.org/intro/article_detail/nmtma/24070.html} }
TY - JOUR T1 - Error Analysis of the Deep Mixed Residual Method for High-Order Elliptic Equations AU - Bai , Mengjia AU - Chen , Jingrun AU - Du , Rui AU - Sun , Zhiwei JO - Numerical Mathematics: Theory, Methods and Applications VL - 2 SP - 395 EP - 436 PY - 2025 DA - 2025/05 SN - 18 DO - http://doi.org/10.4208/nmtma.OA-2024-0134 UR - https://global-sci.org/intro/article_detail/nmtma/24070.html KW - Neural network approximation, deep mixed residual method, high-order elliptic equation. AB -

This paper presents an a priori error analysis of the Deep Mixed Residual method (MIM) for solving high-order elliptic equations with non-homogeneous boundary conditions, including Dirichlet, Neumann, and Robin conditions. We examine MIM with two types of loss functions, referred to as first-order and second-order least squares systems. By providing boundedness and coercivity analysis, we leverage Céa’s Lemma to decompose the total error into the approximation, generalization, and optimization errors. Utilizing the Barron space theory and Rademacher complexity, an a priori error is derived regarding the training samples and network size that are exempt from the curse of dimensionality. Our results reveal that MIM significantly reduces the regularity requirements for activation functions compared to the deep Ritz method, implying the effectiveness of MIM in solving high-order equations.

Bai , MengjiaChen , JingrunDu , Rui and Sun , Zhiwei. (2025). Error Analysis of the Deep Mixed Residual Method for High-Order Elliptic Equations. Numerical Mathematics: Theory, Methods and Applications. 18 (2). 395-436. doi:10.4208/nmtma.OA-2024-0134
Copy to clipboard
The citation has been copied to your clipboard