Spectral properties of kernel matrices in the flat limit

10/30/2019
by   Simon Barthelmé, et al.
0

Kernel matrices are of central importance to many applied fields. In this manuscript, we focus on spectral properties of kernel matrices in the so-called "flat limit", which occurs when points are close together relative to the scale of the kernel. We establish asymptotic expressions for the determinants of the kernel matrices, which we then leverage to obtain asymptotic expressions for the main terms of the eigenvalues. A separate analysis using Kato's perturbation theory yields expressions for limiting eigenvectors, which are strongly tied to discrete orthogonal polynomials. Both smooth and finitely smooth kernels are covered, with stronger results available in the univariate case.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
07/15/2021

Determinantal Point Processes in the Flat Limit

Determinantal point processes (DPPs) are repulsive point processes where...
research
01/04/2022

Gaussian Process Regression in the Flat Limit

Gaussian process (GP) regression is a fundamental tool in Bayesian stati...
research
01/10/2018

Approximation beats concentration? An approximation view on inference with smooth radial kernels

Positive definite kernels and their associated Reproducing Kernel Hilber...
research
02/14/2012

New Probabilistic Bounds on Eigenvalues and Eigenvectors of Random Kernel Matrices

Kernel methods are successful approaches for different machine learning ...
research
12/07/2018

Higher-order Accurate Spectral Density Estimation of Functional Time Series

Under the frequency domain framework for weakly dependent functional tim...
research
03/24/2021

Asymptotic Freeness of Layerwise Jacobians Caused by Invariance of Multilayer Perceptron: The Haar Orthogonal Case

Free Probability Theory (FPT) provides rich knowledge for handling mathe...

Please sign up or login with your details

Forgot password? Click here to reset