Concentration of Measure and Large Random Matrices with an application to Sample Covariance Matrices
Abstract
The present work provides an original framework for random matrix analysis based on revisiting the concentration of measure theory from a probabilistic point of view. By providing various notions of vector concentration (-exponential, linear, Lipschitz, convex), a set of elementary tools is laid out that allows for the immediate extension of classical results from random matrix theory involving random concentrated vectors in place of vectors with independent entries. These findings are exemplified here in the context of sample covariance matrices but find a large range of applications in statistical learning and beyond, thanks to the broad adaptability of our hypotheses.
Keywords
Cite
@article{arxiv.1805.08295,
title = {Concentration of Measure and Large Random Matrices with an application to Sample Covariance Matrices},
author = {Cosme Louart and Romain Couillet},
journal= {arXiv preprint arXiv:1805.08295},
year = {2021}
}
Comments
Concentration of the Measure, Random Matrices, Deterministic equivalent, Talagrand Theorem, Hanson-Wright Theorem, Davis Theorem 82 pages, 3 figures