Efficient Approximation to Analytic and $L^p$ functions by Height-Augmented ReLU Networks

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, ZeYu, Fan, FengLei, Zeng, TieYong
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915855016656896
author Li, ZeYu
Fan, FengLei
Zeng, TieYong
author_facet Li, ZeYu
Fan, FengLei
Zeng, TieYong
contents This work addresses two fundamental limitations in neural network approximation theory. We demonstrate that a three-dimensional network architecture enables a significantly more efficient representation of sawtooth functions, which serves as the cornerstone in the approximation of analytic and $L^p$ functions. First, we establish substantially improved exponential approximation rates for several important classes of analytic functions and offer a parameter-efficient network design. Second, for the first time, we derive a quantitative and non-asymptotic approximation of high orders for general $L^p$ functions. Our techniques advance the theoretical understanding of the neural network approximation in fundamental function spaces and offer a theoretically grounded pathway for designing more parameter-efficient networks.
format Preprint
id arxiv_https___arxiv_org_abs_2603_11128
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Efficient Approximation to Analytic and $L^p$ functions by Height-Augmented ReLU Networks
Li, ZeYu
Fan, FengLei
Zeng, TieYong
Machine Learning
Neural and Evolutionary Computing
68T07, 41A25
This work addresses two fundamental limitations in neural network approximation theory. We demonstrate that a three-dimensional network architecture enables a significantly more efficient representation of sawtooth functions, which serves as the cornerstone in the approximation of analytic and $L^p$ functions. First, we establish substantially improved exponential approximation rates for several important classes of analytic functions and offer a parameter-efficient network design. Second, for the first time, we derive a quantitative and non-asymptotic approximation of high orders for general $L^p$ functions. Our techniques advance the theoretical understanding of the neural network approximation in fundamental function spaces and offer a theoretically grounded pathway for designing more parameter-efficient networks.
title Efficient Approximation to Analytic and $L^p$ functions by Height-Augmented ReLU Networks
topic Machine Learning
Neural and Evolutionary Computing
68T07, 41A25
url https://arxiv.org/abs/2603.11128