Dissertation Talk: Stein's Method for Matrix Concentration

Lecture | May 2 | 3-4 p.m. | 332 Evans Hall

Speaker/Performer: Lester Mackey, University of California, Berkeley

Sponsor: Electrical Engineering and Computer Sciences (EECS)

Motivated by the problem of estimating matrices from sparse random measurements, I will show how Stein’s method of exchangeable pairs can be used to derive concentration inequalities for matrix-valued random elements. When applied to a sum of independent random matrices, this approach yields matrix generalizations of the classical inequalities due to Hoeffding, Bernstein, Khintchine, and Rosenthal. The same technique delivers bounds for sums of dependent random matrices and more general matrix functionals of dependent random elements.

Event Contact: lmackey@cs.berkeley.edu