Matrix Concentration for Products

De Huang; Jonathan Niles-Weed; Joel A. Tropp; Rachel Ward

doi:10.1007/s10208-021-09533-9

Matrix Concentration for Products

De Huang, Jonathan Niles-Weed, Joel A. Tropp, Rachel Ward

Mathematics

Research output: Contribution to journal › Article › peer-review

Abstract

This paper develops nonasymptotic growth and concentration bounds for a product of independent random matrices. These results sharpen and generalize recent work of Henriksen–Ward, and they are similar in spirit to the results of Ahlswede–Winter and of Tropp for a sum of independent random matrices. The argument relies on the uniform smoothness properties of the Schatten trace classes.

Original language	English (US)
Pages (from-to)	1767-1799
Number of pages	33
Journal	Foundations of Computational Mathematics
Volume	22
Issue number	6
DOIs	https://doi.org/10.1007/s10208-021-09533-9
State	Published - Dec 2022

Keywords

Large deviation
Random matrices

ASJC Scopus subject areas

Analysis
Computational Mathematics
Computational Theory and Mathematics
Applied Mathematics

Access to Document

10.1007/s10208-021-09533-9

Cite this

@article{6fe8d0aa903043fe8cd27fe064021733,

title = "Matrix Concentration for Products",

abstract = "This paper develops nonasymptotic growth and concentration bounds for a product of independent random matrices. These results sharpen and generalize recent work of Henriksen–Ward, and they are similar in spirit to the results of Ahlswede–Winter and of Tropp for a sum of independent random matrices. The argument relies on the uniform smoothness properties of the Schatten trace classes.",

keywords = "Large deviation, Random matrices",

author = "De Huang and Jonathan Niles-Weed and Tropp, {Joel A.} and Rachel Ward",

note = "Publisher Copyright: {\textcopyright} 2021, SFoCM.",

year = "2022",

month = dec,

doi = "10.1007/s10208-021-09533-9",

language = "English (US)",

volume = "22",

pages = "1767--1799",

journal = "Foundations of Computational Mathematics",

issn = "1615-3375",

publisher = "Springer New York",

number = "6",

}

TY - JOUR

T1 - Matrix Concentration for Products

AU - Huang, De

AU - Niles-Weed, Jonathan

AU - Tropp, Joel A.

AU - Ward, Rachel

PY - 2022/12

Y1 - 2022/12

N2 - This paper develops nonasymptotic growth and concentration bounds for a product of independent random matrices. These results sharpen and generalize recent work of Henriksen–Ward, and they are similar in spirit to the results of Ahlswede–Winter and of Tropp for a sum of independent random matrices. The argument relies on the uniform smoothness properties of the Schatten trace classes.

AB - This paper develops nonasymptotic growth and concentration bounds for a product of independent random matrices. These results sharpen and generalize recent work of Henriksen–Ward, and they are similar in spirit to the results of Ahlswede–Winter and of Tropp for a sum of independent random matrices. The argument relies on the uniform smoothness properties of the Schatten trace classes.

KW - Large deviation

KW - Random matrices

UR - http://www.scopus.com/inward/record.url?scp=85112392689&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85112392689&partnerID=8YFLogxK

U2 - 10.1007/s10208-021-09533-9

DO - 10.1007/s10208-021-09533-9

M3 - Article

AN - SCOPUS:85112392689

SN - 1615-3375

VL - 22

SP - 1767

EP - 1799

JO - Foundations of Computational Mathematics

JF - Foundations of Computational Mathematics

IS - 6

ER -

Matrix Concentration for Products

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this