English

Error Analysis of the Deep Mixed Residual Method for High-order Elliptic Equations

Numerical Analysis 2024-11-26 v2 Numerical Analysis

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 C\'{e}a'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.

Keywords

Cite

@article{arxiv.2411.14151,
  title  = {Error Analysis of the Deep Mixed Residual Method for High-order Elliptic Equations},
  author = {Mengjia Bai and Jingrun Chen and Rui Du and Zhiwei Sun},
  journal= {arXiv preprint arXiv:2411.14151},
  year   = {2024}
}

Comments

39 pages,

R2 v1 2026-06-28T20:07:48.984Z