Asymptotic Gaussian Fluctuations of Eigenvectors in Spectral Clustering

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lebeau, Hugo, Chatelain, Florent, Couillet, Romain
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929358867791872
author Lebeau, Hugo
Chatelain, Florent
Couillet, Romain
author_facet Lebeau, Hugo
Chatelain, Florent
Couillet, Romain
contents The performance of spectral clustering relies on the fluctuations of the entries of the eigenvectors of a similarity matrix, which has been left uncharacterized until now. In this letter, it is shown that the signal $+$ noise structure of a general spike random matrix model is transferred to the eigenvectors of the corresponding Gram kernel matrix and the fluctuations of their entries are Gaussian in the large-dimensional regime. This CLT-like result was the last missing piece to precisely predict the classification performance of spectral clustering. The proposed proof is very general and relies solely on the rotational invariance of the noise. Numerical experiments on synthetic and real data illustrate the universality of this phenomenon.
format Preprint
id arxiv_https___arxiv_org_abs_2402_12302
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Asymptotic Gaussian Fluctuations of Eigenvectors in Spectral Clustering
Lebeau, Hugo
Chatelain, Florent
Couillet, Romain
Machine Learning
Probability
The performance of spectral clustering relies on the fluctuations of the entries of the eigenvectors of a similarity matrix, which has been left uncharacterized until now. In this letter, it is shown that the signal $+$ noise structure of a general spike random matrix model is transferred to the eigenvectors of the corresponding Gram kernel matrix and the fluctuations of their entries are Gaussian in the large-dimensional regime. This CLT-like result was the last missing piece to precisely predict the classification performance of spectral clustering. The proposed proof is very general and relies solely on the rotational invariance of the noise. Numerical experiments on synthetic and real data illustrate the universality of this phenomenon.
title Asymptotic Gaussian Fluctuations of Eigenvectors in Spectral Clustering
topic Machine Learning
Probability
url https://arxiv.org/abs/2402.12302