Logo

Matrix Concentration for Products

Dc81914328a83a00f1320bdde776b88243fff8a6

Speaker

Jonathan Niles-Weed, New York University, USA

Time

2020.11.19 10:00-11:00

Venue

Online—ZOOM APP

ZOOM Info

Zoom Link: 954-143-37873

Password: 443240

Abstract

We develop nonasymptotic concentration bounds for products of independent random matrices. Such products arise in the study of stochastic algorithms, linear dynamical systems and random walks on groups. Our bounds exactly match those available for scalar random variables and continue the program, initiated by Ahlswede-Winter and Tropp, of extending familiar concentration bounds to the noncommutative setting. Our proof technique relies on geometric properties of the Schatten trace class. Joint work with D. Huang, J. A. Tropp, and R. Ward.

Bio

Jonathan Niles-Weed is an Assistant Professor of Mathematics and Data Science at the Courant Institute of Mathematical Sciences and the Center for Data Science at NYU, where he is a core member of the Math and Data group. He completed his PhD in Mathematics and Statistics at MIT, under the supervision of Philippe Rigollet. His primary area of interest is statistics, probability and mathematics of data science, in particular statistical optimal transport problems.

Sponsors

Video