EFRON-STEIN INEQUALITIES FOR RANDOM MATRICES

成果类型:
Article
署名作者:
Paulin, Daniel; Mackey, Lester; Tropp, Joel A.
署名单位:
National University of Singapore; Stanford University; California Institute of Technology
刊物名称:
ANNALS OF PROBABILITY
ISSN/ISSBN:
0091-1798
DOI:
10.1214/15-AOP1054
发表日期:
2016
页码:
3431-3473
关键词:
random-variables coherence
摘要:
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.