Robin Pre-Training for the Deep Ritz Method
Proceedings of the Northern Lights Deep Learning Workshop · 23.01.2023 · 4
DOI: 10.7557/18.6800 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the Northern Lights Deep Learning Workshop, online erschienen am 23.01.2023. Verfasst von Luca Courte und 1 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 16 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
We analyze the training process of the Deep Ritz Method for elliptic equations with Dirichlet boundary conditions and highlight problems arising from essential boundary values. Typically, one employs a penalty approach to enforce essential boundary conditions, however, the naive approach to this problem becomes unstable for large penalizations. A novel method to compensate this problem is proposed, using a small penalization strength to pre-train the model before the main training on the target penalization strength is conducted. We present numerical evidence that the proposed method is beneficial.
Zitieren
APA
Courte, L., & Zeinhofer, M. (2023). Robin Pre-Training for the Deep Ritz Method. Proceedings of the Northern Lights Deep Learning Workshop, 4. https://doi.org/10.7557/18.6800
Vancouver
Courte L, Zeinhofer M. Robin Pre-Training for the Deep Ritz Method. Proceedings of the Northern Lights Deep Learning Workshop. 2023;4. doi:10.7557/18.6800
BibTeX
@article{Courte2023,
author = {Courte, Luca and Zeinhofer, Marius},
title = {Robin Pre-Training for the Deep Ritz Method},
journal = {Proceedings of the Northern Lights Deep Learning Workshop},
year = {2023},
volume = {4},
doi = {10.7557/18.6800}
}
EUVIMED