On the optimal approximation of Sobolev and Besov functions using deep ReLU neural networks
Applied and Computational Harmonic Analysis · 2025-10 · 79 · 101797
DOI: 10.1016/j.acha.2025.101797 ↗Kurz gefasst
Fachartikel in der Zeitschrift Applied and Computational Harmonic Analysis, 2025-10. Verfasst von Yunfei Yang. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 49 Literaturangaben. Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
This paper studies the problem of how efficiently functions in the Sobolev spaces $\mathcal{W}^{s,q}([0,1]^d)$ and Besov spaces $\mathcal{B}^s_{q,r}([0,1]^d)$ can be approximated by deep ReLU neural networks with width $W$ and depth $L$, when the error is measured in the $L^p([0,1]^d)$ norm. This problem has been studied by several recent works, which obtained the approximation rate $\mathcal{O}((WL)^{-2s/d})$ up to logarithmic factors when $p=q=\infty$, and the rate $\mathcal{O}(L^{-2s/d})$ for networks with fixed width when the Sobolev embedding condition $1/q -1/p
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Yang, Y. (2025). On the optimal approximation of Sobolev and Besov functions using deep ReLU neural networks. Applied and Computational Harmonic Analysis, 79, 101797. https://doi.org/10.1016/j.acha.2025.101797
Vancouver
Yang Y. On the optimal approximation of Sobolev and Besov functions using deep ReLU neural networks. Applied and Computational Harmonic Analysis. 2025;79:101797. doi:10.1016/j.acha.2025.101797
BibTeX
@article{Yang2025,
author = {Yang, Yunfei},
title = {On the optimal approximation of Sobolev and Besov functions using deep ReLU neural networks},
journal = {Applied and Computational Harmonic Analysis},
year = {2025},
volume = {79},
pages = {101797},
doi = {10.1016/j.acha.2025.101797}
}
EUVIMED