Gespeichert in:
Bibliographische Detailangaben
1. Verfasser: Yang, Yunfei
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2504.20617
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866914063473180672
author Yang, Yunfei
author_facet Yang, Yunfei
contents We study the consistency of minimum-norm interpolation in reproducing kernel Hilbert spaces corresponding to bounded kernels. Our main result give lower bounds for the generalization error of the kernel interpolation measured in a continuous scale of norms that interpolate between $L^2$ and the hypothesis space. These lower bounds imply that kernel interpolation is always inconsistent, when the smoothness index of the norm is larger than a constant that depends only on the embedding index of the hypothesis space and the decay rate of the eigenvalues.
format Preprint
id arxiv_https___arxiv_org_abs_2504_20617
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Sobolev norm inconsistency of kernel interpolation
Yang, Yunfei
Machine Learning
We study the consistency of minimum-norm interpolation in reproducing kernel Hilbert spaces corresponding to bounded kernels. Our main result give lower bounds for the generalization error of the kernel interpolation measured in a continuous scale of norms that interpolate between $L^2$ and the hypothesis space. These lower bounds imply that kernel interpolation is always inconsistent, when the smoothness index of the norm is larger than a constant that depends only on the embedding index of the hypothesis space and the decay rate of the eigenvalues.
title Sobolev norm inconsistency of kernel interpolation
topic Machine Learning
url https://arxiv.org/abs/2504.20617