Efron–Stein inequalities for random matrices

Daniel Paulin, Lester Mackey, Joel Tropp

Research output: Contribution to journalArticlepeer-review


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.
Original languageEnglish
Pages (from-to)3431-3473
Number of pages43
JournalAnnals of Probability
Issue number5
Publication statusPublished - 21 Sep 2016
Externally publishedYes


Dive into the research topics of 'Efron–Stein inequalities for random matrices'. Together they form a unique fingerprint.

Cite this