On best approximation by multivariate ridge functions with applications to generalized translation networks

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Geuchen, Paul, Salanevich, Palina, Schavemaker, Olov, Voigtlaender, Felix
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866916818854084608
author Geuchen, Paul
Salanevich, Palina
Schavemaker, Olov
Voigtlaender, Felix
author_facet Geuchen, Paul
Salanevich, Palina
Schavemaker, Olov
Voigtlaender, Felix
contents In this paper, we prove sharp upper and lower bounds for the approximation of Sobolev functions by sums of multivariate ridge functions, i.e., for approximation by functions of the form $\mathbb{R}^d \ni x \mapsto \sum_{k=1}^n \varrho_k(A_k x) \in \mathbb{R}$ with $\varrho_k : \mathbb{R}^\ell \to \mathbb{R}$ and $A_k \in \mathbb{R}^{\ell \times d}$. We show that the order of approximation asymptotically behaves as $n^{-r/(d-\ell)}$, where $r$ is the regularity (order of differentiability) of the Sobolev functions to be approximated. Our lower bound even holds when approximating $L^\infty$-Sobolev functions of regularity $r$ with error measured in $L^1$, while our upper bound applies to the approximation of $L^p$-Sobolev functions in $L^p$ for any $1 \leq p \leq \infty$. These bounds generalize well-known results regarding the approximation properties of univariate ridge functions to the multivariate case. We use our results to obtain sharp asymptotic bounds for the approximation of Sobolev functions using generalized translation networks and complex-valued neural networks.
format Preprint
id arxiv_https___arxiv_org_abs_2412_08453
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle On best approximation by multivariate ridge functions with applications to generalized translation networks
Geuchen, Paul
Salanevich, Palina
Schavemaker, Olov
Voigtlaender, Felix
Functional Analysis
Machine Learning
41A30, 41A25, 41A63, 46E35, 68T07
In this paper, we prove sharp upper and lower bounds for the approximation of Sobolev functions by sums of multivariate ridge functions, i.e., for approximation by functions of the form $\mathbb{R}^d \ni x \mapsto \sum_{k=1}^n \varrho_k(A_k x) \in \mathbb{R}$ with $\varrho_k : \mathbb{R}^\ell \to \mathbb{R}$ and $A_k \in \mathbb{R}^{\ell \times d}$. We show that the order of approximation asymptotically behaves as $n^{-r/(d-\ell)}$, where $r$ is the regularity (order of differentiability) of the Sobolev functions to be approximated. Our lower bound even holds when approximating $L^\infty$-Sobolev functions of regularity $r$ with error measured in $L^1$, while our upper bound applies to the approximation of $L^p$-Sobolev functions in $L^p$ for any $1 \leq p \leq \infty$. These bounds generalize well-known results regarding the approximation properties of univariate ridge functions to the multivariate case. We use our results to obtain sharp asymptotic bounds for the approximation of Sobolev functions using generalized translation networks and complex-valued neural networks.
title On best approximation by multivariate ridge functions with applications to generalized translation networks
topic Functional Analysis
Machine Learning
41A30, 41A25, 41A63, 46E35, 68T07
url https://arxiv.org/abs/2412.08453