Conditional Dependence via Shannon Capacity: Axioms, Estimators and Applications

02/10/2016 ∙ by Weihao Gao, et al. ∙ 0

We conduct an axiomatic study of the problem of estimating the strength of a known causal relationship between a pair of variables. We propose that an estimate of causal strength should be based on the conditional distribution of the effect given the cause (and not on the driving distribution of the cause), and study dependence measures on conditional distributions. 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-k 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.



There are no comments yet.


page 1

page 2

page 3

page 4

Code Repositories


Uniform and Capacitated Mutual Information Estimator

view repo
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.