On Generalization Bounds for Deep Networks Based on Loss Surface Implicit Regularization
IEEE Transactions on Information Theory · 2023-02 · 69 (2) · 1203-1223
DOI: 10.1109/tit.2022.3215088 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Information Theory, 2023-02. Verfasst von Masaaki Imaizumi und 1 weiteren Autor:innen. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 82 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Japan Society for the Promotion of Science (JSPS) KAKENHI, Japan Science and Technology Agency (JST) Presto, Dutch Science Foundation [Nederlandse Organisatie voor Wetenschappelijk Onderzoek (NWO)] through the Vidi.
Abstract (Originalsprache)
Kein Abstract verfügbar.
Förderung
- Japan Society for the Promotion of Science (JSPS) KAKENHI
- Japan Science and Technology Agency (JST) Presto
- Dutch Science Foundation [Nederlandse Organisatie voor Wetenschappelijk Onderzoek (NWO)] through the Vidi
Zitieren
APA
Imaizumi, M., & Schmidt-Hieber, J. (2023). On Generalization Bounds for Deep Networks Based on Loss Surface Implicit Regularization. IEEE Transactions on Information Theory, 69(2), 1203-1223. https://doi.org/10.1109/tit.2022.3215088
Vancouver
Imaizumi M, Schmidt-Hieber J. On Generalization Bounds for Deep Networks Based on Loss Surface Implicit Regularization. IEEE Transactions on Information Theory. 2023;69(2):1203-1223. doi:10.1109/tit.2022.3215088
BibTeX
@article{Imaizumi2023,
author = {Imaizumi, Masaaki and Schmidt-Hieber, Johannes},
title = {On Generalization Bounds for Deep Networks Based on Loss Surface Implicit Regularization},
journal = {IEEE Transactions on Information Theory},
year = {2023},
volume = {69},
number = {2},
pages = {1203--1223},
doi = {10.1109/tit.2022.3215088}
}
EUVIMED