Deep Neural Networks with General Activations: Super-Convergence in Sobolev Norms

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Yang, Yahong, He, Juncai
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866918402560360448
author Yang, Yahong
He, Juncai
author_facet Yang, Yahong
He, Juncai
contents This paper establishes a comprehensive approximation result for deep fully-connected neural networks with commonly-used and general activation functions in Sobolev spaces $W^{n,\infty}$, with errors measured in the $W^{m,p}$-norm for $m < n$ and $1\le p \le \infty$. The derived rates surpass those of classical numerical approximation techniques, such as finite element and spectral methods, exhibiting a phenomenon we refer to as \emph{super-convergence}. Our analysis shows that deep networks with general activations can approximate weak solutions of partial differential equations (PDEs) with superior accuracy compared to traditional numerical methods at the approximation level. Furthermore, this work closes a significant gap in the error-estimation theory for neural-network-based approaches to PDEs, offering a unified theoretical foundation for their use in scientific computing.
format Preprint
id arxiv_https___arxiv_org_abs_2508_05141
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Deep Neural Networks with General Activations: Super-Convergence in Sobolev Norms
Yang, Yahong
He, Juncai
Machine Learning
Numerical Analysis
68T07, 41A30, 35Q68
F.1.1; G.1.2; I.2.6
This paper establishes a comprehensive approximation result for deep fully-connected neural networks with commonly-used and general activation functions in Sobolev spaces $W^{n,\infty}$, with errors measured in the $W^{m,p}$-norm for $m < n$ and $1\le p \le \infty$. The derived rates surpass those of classical numerical approximation techniques, such as finite element and spectral methods, exhibiting a phenomenon we refer to as \emph{super-convergence}. Our analysis shows that deep networks with general activations can approximate weak solutions of partial differential equations (PDEs) with superior accuracy compared to traditional numerical methods at the approximation level. Furthermore, this work closes a significant gap in the error-estimation theory for neural-network-based approaches to PDEs, offering a unified theoretical foundation for their use in scientific computing.
title Deep Neural Networks with General Activations: Super-Convergence in Sobolev Norms
topic Machine Learning
Numerical Analysis
68T07, 41A30, 35Q68
F.1.1; G.1.2; I.2.6
url https://arxiv.org/abs/2508.05141