Saved in:
Bibliographic Details
Main Authors: Dommel, Paul, Lakshmanan, Rajmadan
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2508.11274
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918139297529856
author Dommel, Paul
Lakshmanan, Rajmadan
author_facet Dommel, Paul
Lakshmanan, Rajmadan
contents This paper establishes the first polynomial convergence rates for Gaussian kernel ridge regression (KRR) with a fixed hyperparameter in both the uniform and the $L^{2}$-norm. The uniform convergence result closes a gap in the theoretical understanding of KRR with the Gaussian kernel, where no such rates were previously known. In addition, we prove a polynomial $L^{2}$-convergence rate in the case, where the Gaussian kernel's width parameter is fixed. This also contributes to the broader understanding of smooth kernels, for which previously only sub-polynomial $L^{2}$-rates were known in similar settings. Together, these results provide new theoretical justification for the use of Gaussian KRR with fixed hyperparameters in nonparametric regression.
format Preprint
id arxiv_https___arxiv_org_abs_2508_11274
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Uniform convergence for Gaussian kernel ridge regression
Dommel, Paul
Lakshmanan, Rajmadan
Machine Learning
This paper establishes the first polynomial convergence rates for Gaussian kernel ridge regression (KRR) with a fixed hyperparameter in both the uniform and the $L^{2}$-norm. The uniform convergence result closes a gap in the theoretical understanding of KRR with the Gaussian kernel, where no such rates were previously known. In addition, we prove a polynomial $L^{2}$-convergence rate in the case, where the Gaussian kernel's width parameter is fixed. This also contributes to the broader understanding of smooth kernels, for which previously only sub-polynomial $L^{2}$-rates were known in similar settings. Together, these results provide new theoretical justification for the use of Gaussian KRR with fixed hyperparameters in nonparametric regression.
title Uniform convergence for Gaussian kernel ridge regression
topic Machine Learning
url https://arxiv.org/abs/2508.11274