A universal approximation theorem and its applications to vector lattice theory
Journal of Mathematical Analysis and Applications · 2026-09 · 561 (1) · 130632
DOI: 10.1016/j.jmaa.2026.130632 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Mathematical Analysis and Applications, 2026-09. Verfasst von Eugene Bilokopytov und 1 weiteren Autor:innen. Die Arbeit nennt 31 Literaturangaben. Gefördert von: Pacific Institute for the Mathematical Sciences, Natural Sciences and Engineering Research Council of Canada.
Abstract (Originalsprache)
A classical result in approximation theory states that for any continuous function \( \varphi: \mathbb{R} \to \mathbb{R} \), the set \( \operatorname{span}\{\varphi \circ g : g \in \operatorname{Aff}(\mathbb{R})\} \) is dense in \( \mathcal{C}(\mathbb{R}) \) if and only if \( \varphi \) is not a polynomial. In this note, we present infinite dimensional variants of this result. These extensions apply to neural network architectures and improve the main density result obtained in \cite{BDG23}. We also discuss applications and related approximation results in vector lattices, improving and complementing results from \cite{AT:17, bhp,BT:24}.
Förderung
- Pacific Institute for the Mathematical Sciences
- Natural Sciences and Engineering Research Council of Canada
Zitieren
APA
Bilokopytov, E., & Xanthos, F. (2026). A universal approximation theorem and its applications to vector lattice theory. Journal of Mathematical Analysis and Applications, 561(1), 130632. https://doi.org/10.1016/j.jmaa.2026.130632
Vancouver
Bilokopytov E, Xanthos F. A universal approximation theorem and its applications to vector lattice theory. Journal of Mathematical Analysis and Applications. 2026;561(1):130632. doi:10.1016/j.jmaa.2026.130632
BibTeX
@article{Bilokopytov2026,
author = {Bilokopytov, Eugene and Xanthos, Foivos},
title = {A universal approximation theorem and its applications to vector lattice theory},
journal = {Journal of Mathematical Analysis and Applications},
year = {2026},
volume = {561},
number = {1},
pages = {130632},
doi = {10.1016/j.jmaa.2026.130632}
}
EUVIMED