Convergence analysis of deep Ritz method with over-parameterization.

Neural Netw

Wuhan University, National Center for Applied Mathematics in Hubei, Wuhan, 430072, Asia, China; Wuhan University, Wuhan Institute for Math & AI, Wuhan, 430072, Asia, China; Wuhan University, School of Mathematics and Statistics, Wuhan, 430072, Asia, China; Wuhan University, Hubei Key Laboratory of Computational Science, Wuhan, 430072, Asia, China. Electronic address:

Published: January 2025

The deep Ritz method (DRM) has recently been shown to be a simple and effective method for solving PDEs. However, the numerical analysis of DRM is still incomplete, especially why over-parameterized DRM works remains unknown. This paper presents the first convergence analysis of the over-parameterized DRM for second-order elliptic equations with Robin boundary conditions. We demonstrate that the convergence rate can be controlled by the weight norm, regardless of the number of parameters in the network. To this end, we establish novel approximation results in Sobolev spaces with norm constraints, which have independent significance.

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.neunet.2024.107110DOI Listing

Publication Analysis

Top Keywords

convergence analysis
8
deep ritz
8
ritz method
8
over-parameterized drm
8
analysis deep
4
method over-parameterization
4
over-parameterization deep
4
drm
4
method drm
4
drm simple
4

Similar Publications

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!