MO1.R5.2

An extension of Mcdiarmid's inequality

Richard Combes, CentraleSupelec, France

Session:
Probability and Bounds

Track:
11: Information Theory and Statistics

Location:
Omikron I

Presentation Time:
Mon, 8 Jul, 10:25 - 10:45

Session Chair:
Bobak Nazer, Boston University
Abstract
We generalize McDiarmid's inequality for functions with bounded differences on a high probability set, using an extension argument. Those functions concentrate around their conditional expectations. We illustrate the usefulness of this generalized inequality on a few examples. We further extend the results to concentration in general metric spaces.
Resources