Sharp concentration for sums of matrices with Markovian dependence through universality

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Van Werde, Alexander, Sanders, Jaron
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908998110806016
author Van Werde, Alexander
Sanders, Jaron
author_facet Van Werde, Alexander
Sanders, Jaron
contents We prove that a sum of random matrices generated by a $ψ$-mixing Markov chain has similar spectral properties to a Gaussian matrix with the same mean and covariance structure. This nonasymptotic universality principle enables sharp concentration inequalities when combined with recent advances in the Gaussian literature. We illustrate the theory with examples, showing how it enables polynomial dimensional improvements relative to previous Markovian matrix concentration results when applied to Wigner-type matrices, and how one can recover sharp limiting values for a model used to study spectral clustering techniques. A key challenge in the proof is that techniques based only on classical cumulants, which can be used when summands are independent, are not sufficient on their own for efficient estimates in a Markovian setting. Our approach exploits Boolean cumulants and a change--of--measure argument.
format Preprint
id arxiv_https___arxiv_org_abs_2307_11632
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Sharp concentration for sums of matrices with Markovian dependence through universality
Van Werde, Alexander
Sanders, Jaron
Probability
Operator Algebras
60B20, 60J05, 46L53
We prove that a sum of random matrices generated by a $ψ$-mixing Markov chain has similar spectral properties to a Gaussian matrix with the same mean and covariance structure. This nonasymptotic universality principle enables sharp concentration inequalities when combined with recent advances in the Gaussian literature. We illustrate the theory with examples, showing how it enables polynomial dimensional improvements relative to previous Markovian matrix concentration results when applied to Wigner-type matrices, and how one can recover sharp limiting values for a model used to study spectral clustering techniques. A key challenge in the proof is that techniques based only on classical cumulants, which can be used when summands are independent, are not sufficient on their own for efficient estimates in a Markovian setting. Our approach exploits Boolean cumulants and a change--of--measure argument.
title Sharp concentration for sums of matrices with Markovian dependence through universality
topic Probability
Operator Algebras
60B20, 60J05, 46L53
url https://arxiv.org/abs/2307.11632