On the Existence of Optimal Shallow Feedforward Networks with ReLU Activation
Journal of Machine Learning · 2024
DOI: 10.4208/jml.230903 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Machine Learning, 2024. Verfasst von Steffen Dereich und 1 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 29 Literaturangaben.
Abstract (Originalsprache)
We prove existence of global minima in the loss landscape for the approximation of continuous target functions using shallow feedforward artificial neural networks with ReLU activation. This property is one of the fundamental artifacts separating ReLU from other commonly used activation functions. We propose a kind of closure of the search space so that in the extended space minimizers exist. In a second step, we show under mild assumptions that the newly added functions in the extension perform worse than appropriate representable ReLU networks. This then implies that the optimal response in the extended target space is indeed the response of a ReLU network.
Zitieren
APA
Dereich, S., & Kassing, S. (2024). On the Existence of Optimal Shallow Feedforward Networks with ReLU Activation. Journal of Machine Learning. https://doi.org/10.4208/jml.230903
Vancouver
Dereich S, Kassing S. On the Existence of Optimal Shallow Feedforward Networks with ReLU Activation. Journal of Machine Learning. 2024. doi:10.4208/jml.230903
BibTeX
@article{Dereich2024,
author = {Dereich, Steffen and Kassing, Sebastian},
title = {On the Existence of Optimal Shallow Feedforward Networks with ReLU Activation},
journal = {Journal of Machine Learning},
year = {2024},
doi = {10.4208/jml.230903}
}
EUVIMED