A closer look at covering number bounds for Gaussian kernels

DOI10.1016/J.JCO.2020.101513zbMATH Open1455.68185arXiv1912.11741OpenAlexW3044634373MaRDI QIDQ1996885FDOQ1996885

Authors: Ingo Steinwart, Simon Fischer 

Publication date: 26 February 2021

Published in: Journal of Complexity (Search for Journal in Brave)

Abstract: We establish some new bounds on the log-covering numbers of (anisotropic) Gaussian reproducing kernel Hilbert spaces. Unlike previous results in this direction we focus on small explicit constants and their dependency on crucial parameters such as the kernel bandwidth and the size and dimension of the underlying space.

Full work available at URL: https://arxiv.org/abs/1912.11741

Recommendations

• Covering numbers of Gaussian reproducing kernel Hilbert spaces
• Covering numbers for support vector machines
• The covering number in learning theory
• The covering numbers for some periodic reproducing kernel spaces
• Capacity of reproducing kernel spaces in learning theory

zbMATH Keywords

covering numbersGaussian kernels

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Hilbert spaces with reproducing kernels (= (proper) functional Hilbert spaces, including de Branges-Rovnyak and other structured spaces) (46E22)

Cites Work

• Gaussian processes for machine learning.
• Learning Theory
• Support Vector Machines
• Adaptive Bayesian estimation using a Gaussian random field with inverse gamma bandwidth
• Title not available (Why is that?)
• Title not available (Why is that?)
• The covering number in learning theory
• Capacity of reproducing kernel spaces in learning theory
• ESTIMATING THE APPROXIMATION ERROR IN LEARNING THEORY
• Optimal regression rates for SVMs using Gaussian kernels
• Covering numbers of Gaussian reproducing kernel Hilbert spaces
• Learning rates for kernel-based expectile regression

Cited In (3)

• Covering numbers of Gaussian reproducing kernel Hilbert spaces
• A close look at the entropy numbers of the unit ball of the reproducing Hilbert space of isotropic positive definite kernels
• Cover-based bounds on the numerical rank of Gaussian kernels

This page was built for publication: A closer look at covering number bounds for Gaussian kernels

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1996885)