Matrix Concentration Inequalities via the Method of Exchangeable Pairs
Abstract
This paper derives exponential concentration inequalities and polynomial moment inequalities for the spectral norm of a random matrix. The analysis requires a matrix extension of the scalar concentration theory developed by Sourav Chatterjee using Stein's method of exchangeable pairs. When applied to a sum of independent random matrices, this approach yields matrix generalizations of the classical inequalities due to Hoe ding, Bernstein, Khintchine, and Rosenthal. The same technique delivers bounds for sums of dependent random matrices and more general matrix-valued functions of dependent random variables.
Document Details
- Document Type
- Technical Report
- Publication Date
- Jan 27, 2012
- Accession Number
- ADA563088
Entities
People
- Brendan Farrell
- Joel A. Tropp
- Lester Mackey
- Michael I. Jordan
- Richard Y. Chen
Organizations
- California Institute of Technology