A Wasserstein-based measure of conditional dependence

Abstract

Measuring conditional dependencies among the variables of a network is of great interest to many disciplines. This paper studies some shortcomings of the existing dependency measures in detecting direct causal influences or their lack of ability for group selection to capture strong dependencies and accordingly introduces a new statistical dependency measure to overcome them. This measure is inspired by Dobrushin’s coefficients and based on the fact that there is no dependency betweenXandYgiven another variableZ, if and only if the conditional distribution ofYgiven$$X=x$$X=xand$$Z=z$$Z=zdoes not change whenXtakes another realization$$x'$$x′whileZtakes the same realizationz. We show the advantages of this measure over the related measures in the literature. Moreover, we establish the connection between our measure and the integral probability metric (IPM) that helps to develop estimators of the measure with lower complexity compared to other relevant information theoretic-based measures. Finally, we show the performance of this measure through numerical simulations.

Document Details

Document Type
Pub Defense Publication
Publication Date
Jun 25, 2022
Source ID
10.1007/s41237-022-00170-2

Entities

People

  • Jalal Etesami
  • Kun Zhang
  • Negar Kiyavash

Organizations

  • Office of Naval Research Global
  • Swiss Federal Institute of Technology in Lausanne

Tags

Fields of Study

  • Computer science

Readers

  • Mathematical Modeling and Probability Theory.
  • Statistical inference.
  • Systems Analysis and Design