Convergence analysis of deep Ritz method with over-parameterization.
basic_science · Level V
Where this comes from
- Record sourced from PubMed, PMID 39793492.
- Also identified by DOI 10.1016/j.neunet.2024.107110.
- No licence information is recorded for this record.
- Because redistribution is not established, this page shows the abstract only. Follow the links below for the full text.
Abstract
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.
Medical subject headings
- Neural Networks, Computer
- Algorithms