Interaction Information for Causal Inference: The Case of Directed Triangle
Artificial Intelligence
2017-02-01 v1
Abstract
Interaction information is one of the multivariate generalizations of mutual information, which expresses the amount information shared among a set of variables, beyond the information, which is shared in any proper subset of those variables. Unlike (conditional) mutual information, which is always non-negative, interaction information can be negative. We utilize this property to find the direction of causal influences among variables in a triangle topology under some mild assumptions.
Keywords
Cite
@article{arxiv.1701.08868,
title = {Interaction Information for Causal Inference: The Case of Directed Triangle},
author = {AmirEmad Ghassami and Negar Kiyavash},
journal= {arXiv preprint arXiv:1701.08868},
year = {2017}
}