Saved in:
Bibliographic Details
Main Authors: Morina, Erion, Holler, Martin
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2508.19672
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916920899403776
author Morina, Erion
Holler, Martin
author_facet Morina, Erion
Holler, Martin
contents We show that suitably regular functions can be approximated in the $\mathcal{C}^1$-norm both with rational functions and rational neural networks, including approximation rates with respect to width and depth of the network, and degree of the rational functions. As consequence of our results, we further obtain $\mathcal{C}^1$-approximation results for rational neural networks with the $\text{EQL}^÷$ and ParFam architecture, both of which are important in particular in the context of symbolic regression for physical law learning.
format Preprint
id arxiv_https___arxiv_org_abs_2508_19672
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle $\mathcal{C}^1$-approximation with rational functions and rational neural networks
Morina, Erion
Holler, Martin
Machine Learning
Information Theory
Numerical Analysis
33F05, 41A20, 41A25, 26C15
We show that suitably regular functions can be approximated in the $\mathcal{C}^1$-norm both with rational functions and rational neural networks, including approximation rates with respect to width and depth of the network, and degree of the rational functions. As consequence of our results, we further obtain $\mathcal{C}^1$-approximation results for rational neural networks with the $\text{EQL}^÷$ and ParFam architecture, both of which are important in particular in the context of symbolic regression for physical law learning.
title $\mathcal{C}^1$-approximation with rational functions and rational neural networks
topic Machine Learning
Information Theory
Numerical Analysis
33F05, 41A20, 41A25, 26C15
url https://arxiv.org/abs/2508.19672