Approximation of Functionals by Neural Network Without Curse of Dimensionality
Journal of Machine Learning · 2022
DOI: 10.4208/jml.221018 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Machine Learning, 2022. Verfasst von Yahong Yang und 1 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 37 Literaturangaben.
Abstract (Originalsprache)
In this paper, we establish a neural network to approximate functionals, which are maps from infinite dimensional spaces to finite dimensional spaces. The approximation error of the neural network is $\mathcal{O}(1/\sqrt{m})$ where $m$ is the size of networks. In other words, the error of the network is no dependence on the dimensionality respecting to the number of the nodes in neural networks. The key idea of the approximation is to define a Barron space of functionals.
Zitieren
APA
Yang, Y., & Xiang, Y. (2022). Approximation of Functionals by Neural Network Without Curse of Dimensionality. Journal of Machine Learning. https://doi.org/10.4208/jml.221018
Vancouver
Yang Y, Xiang Y. Approximation of Functionals by Neural Network Without Curse of Dimensionality. Journal of Machine Learning. 2022. doi:10.4208/jml.221018
BibTeX
@article{Yang2022,
author = {Yang, Yahong and Xiang, Yang},
title = {Approximation of Functionals by Neural Network Without Curse of Dimensionality},
journal = {Journal of Machine Learning},
year = {2022},
doi = {10.4208/jml.221018}
}
EUVIMED