Optimal Approximation of Zonoids and Uniform Approximation by Shallow Neural Networks

Fuente: arXiv
Saved in:
Bibliographic Details
Main Author: Siegel, Jonathan W.
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916659791396864
author Siegel, Jonathan W.
author_facet Siegel, Jonathan W.
contents We study the following two related problems. The first is to determine to what error an arbitrary zonoid in $\mathbb{R}^{d+1}$ can be approximated in the Hausdorff distance by a sum of $n$ line segments. The second is to determine optimal approximation rates in the uniform norm for shallow ReLU$^k$ neural networks on their variation spaces. The first of these problems has been solved for $d\neq 2,3$, but when $d=2,3$ a logarithmic gap between the best upper and lower bounds remains. We close this gap, which completes the solution in all dimensions. For the second problem, our techniques significantly improve upon existing approximation rates when $k\geq 1$, and enable uniform approximation of both the target function and its derivatives.
format Preprint
id arxiv_https___arxiv_org_abs_2307_15285
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Optimal Approximation of Zonoids and Uniform Approximation by Shallow Neural Networks
Siegel, Jonathan W.
Machine Learning
Numerical Analysis
41A25, 41A46, 52A21, 68T07
We study the following two related problems. The first is to determine to what error an arbitrary zonoid in $\mathbb{R}^{d+1}$ can be approximated in the Hausdorff distance by a sum of $n$ line segments. The second is to determine optimal approximation rates in the uniform norm for shallow ReLU$^k$ neural networks on their variation spaces. The first of these problems has been solved for $d\neq 2,3$, but when $d=2,3$ a logarithmic gap between the best upper and lower bounds remains. We close this gap, which completes the solution in all dimensions. For the second problem, our techniques significantly improve upon existing approximation rates when $k\geq 1$, and enable uniform approximation of both the target function and its derivatives.
title Optimal Approximation of Zonoids and Uniform Approximation by Shallow Neural Networks
topic Machine Learning
Numerical Analysis
41A25, 41A46, 52A21, 68T07
url https://arxiv.org/abs/2307.15285