Shannon Theory
S.9.2
Lecture
Information Measures I

Strong Asymptotic Composition Theorems for Sibson Mutual Information

Benjamin Huang Wu, Aaron B. Wagner, G. Edward Suh, Ibrahim Issa

Date & Time

01:00 am – 01:00 am

Abstract

We characterize the growth of the Sibson mutual information, of any order that is at least unity, between a random variable and an increasing set of noisy, conditionally independent observations of the random variable. The mutual information increases to an order-dependent limit exponentially fast, with an exponent that is order-independent. The result is constrasted with composition theorems in differential privacy.


Presenters

Benjamin Huang Wu

Cornell University

Aaron B. Wagner

Cornell University

G. Edward Suh

Cornell University

Ibrahim Issa

American University of Beirut

Session Chair

Mokshay Madiman

University of Delaware