Conditional dependence via shannon capacity: Axioms, estimators and applications

We consider axiomatically the problem of estimating the strength of a conditional dependence relationship Py/x fr°m a random variables X to a random variable Y. This has applications in determining the strength of a known causal relationship, where the strength depends only on the conditional distribution of the effect given the cause (and not on the driving distribution of the cause). Shannon capacity, appropriately regularized, emerges as a natural measure under these axioms. We examine the problem of calculating Shannon capacity from the observed samples and propose a novel fixed-A: nearest neighbor estimator, and demonstrate its consistency. Finally, we demonstrate an application to single-cell flow- cytometry, where the proposed estimators significantly reduce sample complexity.