Welcome to the new version of CaltechAUTHORS. Login is currently restricted to library staff. If you notice any issues, please email coda@library.caltech.edu
Published September 4, 2018 | Submitted
Report Open

Deriving Matrix Concentration Inequalities from Kernel Couplings

Abstract

This paper derives exponential tail bounds and polynomial moment inequalities for the spectral norm deviation of a random matrix from its mean value. The argument depends on a matrix extension of Stein's method of exchangeable pairs for concentration of measure, as introduced by Chatterjee. Recent work of Mackey et al. uses these techniques to analyze random matrices with additive structure, while the enhancements in this paper cover a wider class of matrix-valued random elements. In particular, these ideas lead to a bounded differences inequality that applies to random matrices constructed from weakly dependent random variables. The proofs require novel trace inequalities that may be of independent interest.

Additional Information

This paper is based on two independent manuscripts from late 2012 that both used kernel couplings to establish matrix concentration inequalities. One manuscript is by Paulin; the other is by Mackey and Tropp. The authors have combined this research into a unified presentation, with equal contributions from both groups. Paulin thanks his thesis advisors, Louis Chen and Adrian Röllin, for their helpful comments on this manuscript. Tropp was supported by ONR awards N00014-08-1-0883 and N00014-11-1002, AFOSR award FA9550-09-1-0643, and a Sloan Research Fellowship.

Attached Files

Submitted - 1305.0612.pdf

Files

1305.0612.pdf
Files (368.5 kB)
Name Size Download all
md5:f254df41c697024df36943c2964b304c
368.5 kB Preview Download

Additional details

Created:
August 19, 2023
Modified:
October 18, 2023