Gaussian RBF Centered Kernel Alignment (CKA) in the Large Bandwidth Limit
Machine Learning
2026-05-28 v1 Machine Learning
Abstract
We prove that Centered Kernel Alignment (CKA) based on a Gaussian RBF kernel converges to linear CKA in the large-bandwidth limit. We show that convergence onset is sensitive to the geometry of the feature representations, and that representation eccentricity bounds the range of bandwidths for which Gaussian CKA behaves nonlinearly.
Cite
@article{arxiv.2112.09305,
title = {Gaussian RBF Centered Kernel Alignment (CKA) in the Large Bandwidth Limit},
author = {Sergio A. Alvarez},
journal= {arXiv preprint arXiv:2112.09305},
year = {2026}
}
Comments
11 pages, 3 figures