Shared Information for a Markov Chain on a Tree

Shared information is a measure of mutual dependence among m ≥ 2 jointly distributed discrete random variables. For a Markov chain on a tree with a given joint distribution, we give a new proof of an explicit characterization of shared information. When the joint distribution is not known, we exploit the special form of this characterization to provide a multiarmed bandit algorithm for estimating shared information, and analyze its error performance.