Blessing of dimensionality in cross-validated bandwidth selection on the sphere

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chacón, José E., García-Portugués, Eduardo, Meilán-Vila, Andrea
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908793353273344
author Chacón, José E.
García-Portugués, Eduardo
Meilán-Vila, Andrea
author_facet Chacón, José E.
García-Portugués, Eduardo
Meilán-Vila, Andrea
contents We study the asymptotic behavior of least-squares cross-validation bandwidth selection in kernel density estimation on the $d$-dimensional hypersphere, $d\geq 1$. We show that the exact rate of convergence with respect to the optimal bandwidth minimizing the mean integrated squared error, shown to exist under mild non-uniformity conditions, is $n^{-d/(2d+8)}$, thus approaching the $n^{-1/2}$ parametric rate as $d$ grows. This ``blessing of dimensionality'' in bandwidth selection offers theoretical support for utilizing the conceptually simpler cross-validation selector over plug-in techniques for larger dimensions $d$. We compare this result for bandwidth estimation on the $d$-dimensional Euclidean space through explicit expressions for the asymptotic variance functionals. Numerical experiments corroborate the speed of this convergence in an array of scenarios and dimensions, precisely illustrating the tipping dimension where cross-validation outperforms plug-in approaches.
format Preprint
id arxiv_https___arxiv_org_abs_2601_20442
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Blessing of dimensionality in cross-validated bandwidth selection on the sphere
Chacón, José E.
García-Portugués, Eduardo
Meilán-Vila, Andrea
Statistics Theory
Methodology
62H11, 62G07, 62G20
We study the asymptotic behavior of least-squares cross-validation bandwidth selection in kernel density estimation on the $d$-dimensional hypersphere, $d\geq 1$. We show that the exact rate of convergence with respect to the optimal bandwidth minimizing the mean integrated squared error, shown to exist under mild non-uniformity conditions, is $n^{-d/(2d+8)}$, thus approaching the $n^{-1/2}$ parametric rate as $d$ grows. This ``blessing of dimensionality'' in bandwidth selection offers theoretical support for utilizing the conceptually simpler cross-validation selector over plug-in techniques for larger dimensions $d$. We compare this result for bandwidth estimation on the $d$-dimensional Euclidean space through explicit expressions for the asymptotic variance functionals. Numerical experiments corroborate the speed of this convergence in an array of scenarios and dimensions, precisely illustrating the tipping dimension where cross-validation outperforms plug-in approaches.
title Blessing of dimensionality in cross-validated bandwidth selection on the sphere
topic Statistics Theory
Methodology
62H11, 62G07, 62G20
url https://arxiv.org/abs/2601.20442