Efron-Stein Inequalities for Random Matrices
Probability
2014-08-18 v1 Functional Analysis
Abstract
This paper establishes new concentration inequalities for random matrices constructed from independent random variables. These results are analogous with the generalized Efron-Stein inequalities developed by Boucheron et al. The proofs rely on the method of exchangeable pairs.
Keywords
Cite
@article{arxiv.1408.3470,
title = {Efron-Stein Inequalities for Random Matrices},
author = {Daniel Paulin and Lester Mackey and Joel A. Tropp},
journal= {arXiv preprint arXiv:1408.3470},
year = {2014}
}
Comments
42 pages. arXiv admin note: text overlap with arXiv:1305.0612