|COOKIES: By using this website you agree that we can place Google Analytics Cookies on your device for performance monitoring.|
Matrix Concentration Inequalities via the Method of Exchangeable Pairs
If you have a question about this talk, please contact Zoubin Ghahramani.
I will present an approach to deriving exponential concentration inequalities and polynomial moment inequalities for the spectral norm of a random matrix based on Stein’s method of exchangeable pairs. Our work extends results by Chatterjee on concentration for scalar random variables to the setting of random matrices. 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-valued functions of dependent random variables.
This talk is part of the Machine Learning @ CUED series.
This talk is included in these lists:
Note that ex-directory lists are not shown.
Other listsSpecial Lecture Series: THE NATURAL COOK: A THEORY OF HUMAN EVOLUTION The Ellen McArthur Lectures 2013 Lattice field theory informal seminars
Other talksCambridge ESRC DTC Annual Lecture 2017: After Brexit, UKRI if you want to: a social scientist's field guide to the new research landscape Bioinspired adhesive coacervates. Can we exploit companion dogs to advance therapies for spinal cord injury? The Dr Raj Chandavarkar Seminar: - Deep time and the colonial present: a prologue to the history writings of 'Kesari' Balakrishna Pillai "The Shaman is the White Man's Computer": The interaction of shamanism and conservation in Amazonian Guyana Revealing the charge carrier dynamics in metal halide perovskites using time-resolved microwave conductivity