Dimension lower bounds for linear approaches to function approximation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Author: Hsu, Daniel
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912541891887104
author Hsu, Daniel
author_facet Hsu, Daniel
contents This short note presents a linear algebraic approach to proving dimension lower bounds for linear methods that solve $L^2$ function approximation problems. The basic argument has appeared in the literature before (e.g., Barron, 1993) for establishing lower bounds on Kolmogorov $n$-widths. The argument is applied to give sample size lower bounds for kernel methods.
format Preprint
id arxiv_https___arxiv_org_abs_2508_13346
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Dimension lower bounds for linear approaches to function approximation
Hsu, Daniel
Machine Learning
Statistics Theory
This short note presents a linear algebraic approach to proving dimension lower bounds for linear methods that solve $L^2$ function approximation problems. The basic argument has appeared in the literature before (e.g., Barron, 1993) for establishing lower bounds on Kolmogorov $n$-widths. The argument is applied to give sample size lower bounds for kernel methods.
title Dimension lower bounds for linear approaches to function approximation
topic Machine Learning
Statistics Theory
url https://arxiv.org/abs/2508.13346