Extremal Eigenvalues of Random Kernel Matrices with Polynomial Scaling

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Kogan, David, Nandy, Sagnik, Huang, Jiaoyang
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866914985317236736
author Kogan, David
Nandy, Sagnik
Huang, Jiaoyang
author_facet Kogan, David
Nandy, Sagnik
Huang, Jiaoyang
contents We study the spectral norm of random kernel matrices with polynomial scaling, where the number of samples scales polynomially with the data dimension. In this regime, Lu and Yau (2022) proved that the empirical spectral distribution converges to the additive free convolution of a semicircle law and a Marcenko-Pastur law. We demonstrate that the random kernel matrix can be decomposed into a "bulk" part and a low-rank part. The spectral norm of the "bulk" part almost surely converges to the edge of the limiting spectrum. In the special case where the random kernel matrices correspond to the inner products of random tensors, the empirical spectral distribution converges to the Marcenko-Pastur law. We prove that the largest and smallest eigenvalues converge to the corresponding spectral edges of the Marcenko-Pastur law.
format Preprint
id arxiv_https___arxiv_org_abs_2410_17515
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Extremal Eigenvalues of Random Kernel Matrices with Polynomial Scaling
Kogan, David
Nandy, Sagnik
Huang, Jiaoyang
Probability
Statistics Theory
We study the spectral norm of random kernel matrices with polynomial scaling, where the number of samples scales polynomially with the data dimension. In this regime, Lu and Yau (2022) proved that the empirical spectral distribution converges to the additive free convolution of a semicircle law and a Marcenko-Pastur law. We demonstrate that the random kernel matrix can be decomposed into a "bulk" part and a low-rank part. The spectral norm of the "bulk" part almost surely converges to the edge of the limiting spectrum. In the special case where the random kernel matrices correspond to the inner products of random tensors, the empirical spectral distribution converges to the Marcenko-Pastur law. We prove that the largest and smallest eigenvalues converge to the corresponding spectral edges of the Marcenko-Pastur law.
title Extremal Eigenvalues of Random Kernel Matrices with Polynomial Scaling
topic Probability
Statistics Theory
url https://arxiv.org/abs/2410.17515