English

Potential Conditional Mutual Information: Estimators, Properties and Applications

Information Theory 2017-10-16 v1 Machine Learning math.IT Machine Learning

Abstract

The conditional mutual information I(X;Y|Z) measures the average information that X and Y contain about each other given Z. This is an important primitive in many learning problems including conditional independence testing, graphical model inference, causal strength estimation and time-series problems. In several applications, it is desirable to have a functional purely of the conditional distribution p_{Y|X,Z} rather than of the joint distribution p_{X,Y,Z}. We define the potential conditional mutual information as the conditional mutual information calculated with a modified joint distribution p_{Y|X,Z} q_{X,Z}, where q_{X,Z} is a potential distribution, fixed airport. We develop K nearest neighbor based estimators for this functional, employing importance sampling, and a coupling trick, and prove the finite k consistency of such an estimator. We demonstrate that the estimator has excellent practical performance and show an application in dynamical system inference.

Keywords

Cite

@article{arxiv.1710.05012,
  title  = {Potential Conditional Mutual Information: Estimators, Properties and Applications},
  author = {Arman Rahimzamani and Sreeram Kannan},
  journal= {arXiv preprint arXiv:1710.05012},
  year   = {2017}
}
R2 v1 2026-06-22T22:13:01.854Z