On the Growth of the Parameters of a Class of Approximating ReLU Neural Networks

This work focuses on the analysis of a class of fully connected feed forward ReLU neural networks as they approximate a given, smooth function. In contrast to conventionally studied universal approximation properties under increasing architectures, e.g., in terms of width or depth of the networks, we are concerned with the asymptotic growth of the norm of the parameters of approximating networks. Such results are of interest, e.g., for error analysis or consistency results for neural network training. The main result of our work is that, for a class of ReLU architectures with state of the art approximation error, the norm of the realizing parameters grows at most polynomially. The obtained rate with respect to a normalized network size is compared to existing results and is shown to be superior in most cases, in particular for high dimensional input.

Authors

Institutions

Publication Details

Journal
Constructive Approximation
Published
2026-11-19
DOI
https://doi.org/10.1007/s00365-026-09797-w
Citations
4
Primary Topic
Neural Networks and Applications
Type
article
Field-Weighted Citation Impact
1.94
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

On the Growth of the Parameters of a Class of Approximating ReLU Neural Networks

Martin Höller, Erion Morina
4 citations
Constructive Approximation
Neural Networks and Applications
1.94
article

On the Growth of the Parameters of a Class of Approximating ReLU Neural Networks

Martin Höller, Erion Morina
article en
4 citations

Abstract

This work focuses on the analysis of a class of fully connected feed forward ReLU neural networks as they approximate a given, smooth function. In contrast to conventionally studied universal approximation properties under increasing architectures, e.g., in terms of width or depth of the networks, we are concerned with the asymptotic growth of the norm of the parameters of approximating networks. Such results are of interest, e.g., for error analysis or consistency results for neural network training. The main result of our work is that, for a class of ReLU architectures with state of the art approximation error, the norm of the realizing parameters grows at most polynomially. The obtained rate with respect to a normalized network size is compared to existing results and is shown to be superior in most cases, in particular for high dimensional input.

Constructive Approximation
University of Graz (AT)
Openalex Percentile: Top 13%
Neural Networks and Applications
1.94
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon