Bernstein-type inequality for a class of dependent random matrices

DOI10.1142/S2010326316500064MaRDI QIDQ2809331zbMATH OpenFDO

Authors Marwa Banna, Florence Merlevède, Pierre Youssef

Publication date 27 May 2016

Published in Random Matrices: Theory and Applications (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1504.05834

zbMATH Keywords

random matricesBernstein inequalityabsolute regularitydeviation inequality\(\beta\)-mixing coefficients

Mathematics Subject Classification ID

Large deviations (60F10) Random matrices (probabilistic aspects) (60B20)

Abstract: In this paper we obtain a Bernstein type inequality for the sum of self-adjoint centered and geometrically absolutely regular random matrices with bounded largest eigenvalue. This inequality can be viewed as an extension to the matrix setting of the Bernstein-type inequality obtained by Merlev`ede et al. (2009) in the context of real-valued bounded random variables that are geometrically absolutely regular. The proofs rely on decoupling the Laplace transform of a sum on a Cantor-like set of random matrices.

Recommendations

• On some extensions of Bernstein's inequality for self-adjoint operators
• A Bernstein type inequality and moderate deviations for weakly dependent sequences
• Matrix concentration inequalities via the method of exchangeable pairs
• A Bernstein type inequality for NOD random variables and applications
• User-friendly tail bounds for sums of random matrices

Cites work

• scientific article; zbMATH DE number 3692406 (Why is no real title available?)
• scientific article; zbMATH DE number 6026126 (Why is no real title available?)
• A Bernstein type inequality and moderate deviations for weakly dependent sequences
• A tail inequality for suprema of unbounded empirical processes with applications to Markov chains
• Bernstein inequality and moderate deviations under strong mixing conditions
• Convex trace functions and the Wigner-Yanase-Dyson conjecture
• Efron-Stein inequalities for random matrices
• Matrix concentration inequalities via the method of exchangeable pairs
• On Strong Mixing Conditions for Stationary Gaussian Processes
• Strong converse for identification via quantum channels
• User-friendly tail bounds for sums of random matrices

Cited in

(7)

• A bound of the \(\beta\)-mixing coefficient for point processes in terms of their intensity functions
• An exponential inequality for U-statistics under mixing conditions
• On some extensions of Bernstein's inequality for self-adjoint operators
• Rate-optimal robust estimation of high-dimensional vector autoregressive models
• Singular value distribution of dense random matrices with block Markovian dependence
• Matrix Poincaré inequalities and concentration
• Moment bounds for large autocovariance matrices under dependence

This page was built for publication: Bernstein-type inequality for a class of dependent random matrices

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2809331)