On spectral clustering under non-isotropic Gaussian mixture models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kawamoto, Kohei, Goto, Yuichi, Tsukuda, Koji
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915928899321856
author Kawamoto, Kohei
Goto, Yuichi
Tsukuda, Koji
author_facet Kawamoto, Kohei
Goto, Yuichi
Tsukuda, Koji
contents We evaluate the misclustering probability of a spectral clustering algorithm under a Gaussian mixture model with a general covariance structure. The algorithm partitions the data into two groups based on the sign of the first principal component score. As a corollary of the main result, the clustering procedure is shown to be consistent in a high-dimensional regime.
format Preprint
id arxiv_https___arxiv_org_abs_2601_13930
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle On spectral clustering under non-isotropic Gaussian mixture models
Kawamoto, Kohei
Goto, Yuichi
Tsukuda, Koji
Statistics Theory
62H30, 62H25, 62H12
We evaluate the misclustering probability of a spectral clustering algorithm under a Gaussian mixture model with a general covariance structure. The algorithm partitions the data into two groups based on the sign of the first principal component score. As a corollary of the main result, the clustering procedure is shown to be consistent in a high-dimensional regime.
title On spectral clustering under non-isotropic Gaussian mixture models
topic Statistics Theory
62H30, 62H25, 62H12
url https://arxiv.org/abs/2601.13930