English
Related papers

Related papers: Eigenvector overlaps in large sample covariance ma…

200 papers

The aim of this paper is to establish several deep theoretical properties of principal component analysis for multiple-component spike covariance models. Our new results reveal a surprising asymptotic conical structure in critical sample…

Statistics Theory · Mathematics 2013-03-26 Dan Shen , Haipeng Shen , Hongtu Zhu , J. S. Marron

In this paper, we investigate the asymptotic behaviors of the extreme eigenvectors in a general spiked covariance matrix, where the dimension and sample size increase proportionally. We eliminate the restrictive assumption of the block…

Statistics Theory · Mathematics 2024-05-15 Zhangni Pu , Xiaozhuo Zhang , Jiang Hu , Zhidong Bai

Non-Hermitian random matrices with statistical spectral characteristics beyond the standard Ginibre ensembles have recently emerged in the description of dissipative quantum many-body systems as well as in non-ergodic wave transport in…

Mathematical Physics · Physics 2025-11-27 Gernot Akemann , Yan V. Fyodorov , Dmitry V. Savin

Estimating the eigenvalues of a population covariance matrix from a sample covariance matrix is a problem of fundamental importance in multivariate statistics; the eigenvalues of covariance matrices play a key role in many widely…

Statistics Theory · Mathematics 2007-06-13 Noureddine El Karoui

We consider the problem of approximating the set of eigenvalues of the covariance matrix of a multivariate distribution (equivalently, the problem of approximating the "population spectrum"), given access to samples drawn from the…

Machine Learning · Computer Science 2017-07-18 Weihao Kong , Gregory Valiant

A popular regularized (shrinkage) covariance estimator is the shrinkage sample covariance matrix (SCM) which shares the same set of eigenvectors as the SCM but shrinks its eigenvalues toward its grand mean. In this paper, a more general…

Methodology · Statistics 2020-02-13 Esa Ollila , Daniel P. Palomar , Frederic Pascal

We study high-dimensional sample covariance matrices based on independent random vectors with missing coordinates. The presence of missing observations is common in modern applications such as climate studies or gene expression…

Probability · Mathematics 2016-03-01 Kamil Jurczak , Angelika Rohde

Scaling laws for neural networks, in which the loss decays as a power-law in the number of parameters, data, and compute, depend fundamentally on the spectral structure of the data covariance, with power-law eigenvalue decay appearing…

Machine Learning · Statistics 2026-03-17 Elliot Paquette , Ke Liang Xiao , Yizhe Zhu

In this paper, we consider the singular values and singular vectors of finite, low rank perturbations of large rectangular random matrices. Specifically, we prove almost sure convergence of the extreme singular values and appropriate…

Probability · Mathematics 2012-01-27 Florent Benaych-Georges , Raj Rao Nadakuditi

We prove a new CLT for the difference of linear eigenvalue statistics of a Wigner random matrix $H$ and its minor $\hat H$ and find that the fluctuation is much smaller than the fluctuations of the individual linear statistics, as a…

Probability · Mathematics 2018-07-11 László Erdős , Dominik Schröder

We suggest a method of studying the joint probability density (JPD) of an eigenvalue and the associated 'non-orthogonality overlap factor' (also known as the 'eigenvalue condition number') of the left and right eigenvectors for…

Mathematical Physics · Physics 2018-09-21 Yan V Fyodorov

This work is concerned with finite range bounds on the variance of individual eigenvalues of random covariance matrices, both in the bulk and at the edge of the spectrum. In a preceding paper, the author established analogous results for…

Probability · Mathematics 2013-09-25 Sandrine Dallaporta

We introduce an estimation method of covariance matrices in a high-dimensional setting, i.e., when the dimension of the matrix, , is larger than the sample size . Specifically, we propose an orthogonally equivariant estimator. The…

Statistics Theory · Mathematics 2020-12-04 Samprit Banerjee , Stefano Monni

In this paper, we use a new approach to prove that the largest eigenvalue of the sample covariance matrix of a normally distributed vector is bigger than the true largest eigenvalue with probability 1 when the dimension is infinite. We…

Probability · Mathematics 2017-08-14 Soufiane Hayou

This manuscript presents an approach to perform generalized linear regression with multiple high dimensional covariance matrices as the outcome. Model parameters are proposed to be estimated by maximizing a pseudo-likelihood. When the data…

Methodology · Statistics 2020-07-28 Yi Zhao , Brian S. Caffo , Xi Luo

We study the eigenvalues and the eigenvectors of $N\times N$ structured random matrices of the form $H = W\tilde{H}W+D$ with diagonal matrices $D$ and $W$ and $\tilde{H}$ from the Gaussian Unitary Ensemble. Using the supersymmetry technique…

Mathematical Physics · Physics 2018-08-20 Kevin Truong , Alexander Ossipov

In many astrophysical settings covariance matrices of large datasets have to be determined empirically from a finite number of mock realisations. The resulting noise degrades inference and precludes it completely if there are fewer…

Instrumentation and Methods for Astrophysics · Physics 2017-01-11 Benjamin Joachimi

This paper is concerned with the asymptotic distribution of the largest eigenvalues for some nonlinear random matrix ensemble stemming from the study of neural networks. More precisely we consider $M= \frac{1}{m} YY^\top$ with $Y=f(WX)$…

Probability · Mathematics 2022-01-14 Lucas Benigni , Sandrine Péché

This paper investigates a statistical procedure for testing the equality of two independent estimated covariance matrices when the number of potentially dependent data vectors is large and proportional to the size of the vectors, that is,…

Statistics Theory · Mathematics 2020-03-09 Rémy Mariétan , Stephan Morgenthaler

This work analyzes singular-value spectra of weight matrices in pretrained transformer models to understand how information is stored at both ends of the spectrum. Using Random Matrix Theory (RMT) as a zero information hypothesis, we…

Machine Learning · Computer Science 2025-11-07 Max Staats , Matthias Thamm , Bernd Rosenow