Computing the unique information

Given a set of predictor variables and a response variable, how much information do the predictors have about the response, and how is this information distributed between unique, complementary, and shared components? Recent work has proposed to quantify the unique component of the decomposition as the minimum value of the conditional mutual information over a constrained set of information channels. We present an efficient iterative divergence minimization algorithm to solve this optimization problem with convergence guarantees, and we evaluate its performance against other techniques.

Joint work with Johannes Rauh and Guido Montúfar (https://arxiv.org/abs/1709.07487)