Distributed cooperative information bottleneck

This paper investigates a scenario where two distant nodes separately observe memoryless process, namely X 1 and X 2 , and can cooperate through multiple exchanges of messages with the goal of enabling a third node to learn "relevant information" (measured in terms of a multi-letter mutual...

Full description

Saved in:
Bibliographic Details
Published in:Proceedings / IEEE International Symposium on Information Theory pp. 709 - 713
Main Authors: Vera, Matias, Rey Vega, Leonardo, Piantanida, Pablo
Format: Conference Proceeding
Language:English
Published: IEEE 01.06.2017
Subjects:
Distortion
Distributed Source Coding
Electronic mail
Information Bottleneck
Interactive Lossy Source Coding
Markov processes
Mutual information
Random variables
Shannon theory
Source coding
ISSN:2157-8117
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This paper investigates a scenario where two distant nodes separately observe memoryless process, namely X 1 and X 2 , and can cooperate through multiple exchanges of messages with the goal of enabling a third node to learn "relevant information" (measured in terms of a multi-letter mutual information) about some hidden memoryless process Y, which is arbitrarily dependent on (X 1 , X 2 ). These interactive exchanges yield an explicit cooperation that helps the third node to identify, from the distributed observations X 1 and X 2 , useful features for the inference of Y. An inner and an outer bound to the rate-relevance region of this problem is derived. Optimal characterization of the rate-relevance region under two different conditions on the dependence structures of the involved variables is showed. Also, two examples for Gaussian sources are studied.
ISSN:2157-8117
DOI:10.1109/ISIT.2017.8006620