Universality and sharp matrix concentration inequalities

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Brailovskaya, Tatiana, van Handel, Ramon
Formato: Preprint
Publicado: 2022
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866929399166664704
author Brailovskaya, Tatiana
van Handel, Ramon
author_facet Brailovskaya, Tatiana
van Handel, Ramon
contents We show that, under mild assumptions, the spectrum of a sum of independent random matrices is close to that of the Gaussian random matrix whose entries have the same mean and covariance. This nonasymptotic universality principle yields sharp matrix concentration inequalities for general sums of independent random matrices when combined with the Gaussian theory of Bandeira, Boedihardjo, and Van Handel. A key feature of the resulting theory is that it is applicable to a broad class of random matrix models that may have highly nonhomogeneous and dependent entries, which can be far outside the mean-field situation considered in classical random matrix theory. We illustrate the theory in applications to random graphs, matrix concentration inequalities for smallest singular values, sample covariance matrices, strong asymptotic freeness, and phase transitions in spiked models.
format Preprint
id arxiv_https___arxiv_org_abs_2201_05142
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle Universality and sharp matrix concentration inequalities
Brailovskaya, Tatiana
van Handel, Ramon
Probability
Functional Analysis
Operator Algebras
60B20, 60E15, 46L53, 46L54, 15B52
We show that, under mild assumptions, the spectrum of a sum of independent random matrices is close to that of the Gaussian random matrix whose entries have the same mean and covariance. This nonasymptotic universality principle yields sharp matrix concentration inequalities for general sums of independent random matrices when combined with the Gaussian theory of Bandeira, Boedihardjo, and Van Handel. A key feature of the resulting theory is that it is applicable to a broad class of random matrix models that may have highly nonhomogeneous and dependent entries, which can be far outside the mean-field situation considered in classical random matrix theory. We illustrate the theory in applications to random graphs, matrix concentration inequalities for smallest singular values, sample covariance matrices, strong asymptotic freeness, and phase transitions in spiked models.
title Universality and sharp matrix concentration inequalities
topic Probability
Functional Analysis
Operator Algebras
60B20, 60E15, 46L53, 46L54, 15B52
url https://arxiv.org/abs/2201.05142