Universality and Sharp Matrix Concentration Inequalities

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 inde...

Full description

Saved in:
Bibliographic Details
Published inGeometric and functional analysis Vol. 34; no. 6; pp. 1734 - 1838
Main Authors Brailovskaya, Tatiana, van Handel, Ramon
Format Journal Article
LanguageEnglish
Published Cham Springer International Publishing 01.12.2024
Springer Nature B.V
Subjects
Analysis
Covariance matrix
Inequalities
Mathematics
Mathematics and Statistics
Matrix theory
Phase transitions
Principle of universality
60E15
15B52
Random matrices
Free probability
Matrix concentration
60B20
Universality
46L53
46L54
Online AccessGet full text

Cover

More Information
Summary: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.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1016-443X
1420-8970
DOI:10.1007/s00039-024-00692-9