On Convergence Rates of Spiked Eigenvalue Estimates: A General Study of Global and Local Laws in Sample Covariance Matrices

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Jing, Bing-Yi, Li, Weiming, Xie, Jiahui, Zhang, Yangchun, Zhou, Wang
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866909886907940864
author Jing, Bing-Yi
Li, Weiming
Xie, Jiahui
Zhang, Yangchun
Zhou, Wang
author_facet Jing, Bing-Yi
Li, Weiming
Xie, Jiahui
Zhang, Yangchun
Zhou, Wang
contents This paper investigates global and local laws for sample covariance matrices with general growth rates of dimensions. The sample size $N$ and population dimension $M$ can have the same order in logarithm, which implies that their ratio $M/N$ can approach zero, a constant, or infinity. These theories are utilized to determine the convergence rate of spiked eigenvalue estimates.
format Preprint
id arxiv_https___arxiv_org_abs_2511_02456
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle On Convergence Rates of Spiked Eigenvalue Estimates: A General Study of Global and Local Laws in Sample Covariance Matrices
Jing, Bing-Yi
Li, Weiming
Xie, Jiahui
Zhang, Yangchun
Zhou, Wang
Statistics Theory
This paper investigates global and local laws for sample covariance matrices with general growth rates of dimensions. The sample size $N$ and population dimension $M$ can have the same order in logarithm, which implies that their ratio $M/N$ can approach zero, a constant, or infinity. These theories are utilized to determine the convergence rate of spiked eigenvalue estimates.
title On Convergence Rates of Spiked Eigenvalue Estimates: A General Study of Global and Local Laws in Sample Covariance Matrices
topic Statistics Theory
url https://arxiv.org/abs/2511.02456