Learning from Pairwise Marginal Independencies

Johannes Textor, Alexander Idelberger, Maciej Liskiewicz


We consider graphs that represent pairwise marginal independencies amongst a set of variables (for instance, the zero entries of a covari-ance matrix for normal data). We characterize the directed acyclic graphs (DAGs) that faithfully explain a given set of independencies, and derive algorithms to efficiently enumerate such structures. Our results map out the space of faithful causal models for a given set of pairwise marginal independence relations. This allows us to show the extent to which causal inference is possible without using conditional independence tests.

Original languageEnglish
Title of host publicationThe 31st Conference on Uncertainty in Artificial Intelligence (UAI 2015)
Number of pages10
PublisherAUAI Press
Publication date02.08.2015
ISBN (Print)978-0-9966431-0-8
Publication statusPublished - 02.08.2015
EventThe 31st Conference on Uncertainty in Artificial Intelligence (UAI'15) - Amsterdam, Netherlands
Duration: 12.07.201512.07.2015


Dive into the research topics of 'Learning from Pairwise Marginal Independencies'. Together they form a unique fingerprint.

Cite this