Distributed cooperative information bottleneck

Matías Vera, Leonardo Rey Vega, Pablo Piantanida

Abstract: This paper investigates a scenario where two distant nodes separately observe memoryless process, namely X <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sub> and X <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sub> , 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 <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sub> , X <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sub> ). These interactive exchanges yield an explicit cooperation that helps the third node to identify, from the distributed observations X <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sub> and X <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sub> , 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.