A transformational characterization of Markov equivalence for directed acyclic graphs with latent variables

Jiji Zhang, Peter Spirtes

Research output: Chapter in book/report/conference proceedingConference contributionpeer-review

Abstract

Different directed acyclic graphs (DAGs) may be Markov equivalent in the sense that they entail the same conditional independence relations among the observed variables. Chickering (1995) provided a transformational characterization of Markov equivalence for DAGs (with no latent variables), which is useful in deriving properties shared by Markov equivalent DAGs, and, with certain generalization, is needed to prove the asymptotic correctness of a search procedure over Markov equivalence classes, known as the GES algorithm. For DAG models with latent variables, maximal ancestral graphs (MAGs) provide a neat representation that facilitates model search. However, no transformational characterization -- analogous to Chickering's -- of Markov equivalent MAGs is yet available. This paper establishes such a characterization for directed MAGs, which we expect will have similar uses as it does for DAGs.
Original languageEnglish
Title of host publicationProceedings of the 21st Conference on Uncertainty in Artificial Intelligence (UAI)
EditorsFahiem Bacchus, Tommi Jaakkola
PublisherAUAI Press
Pages667–674
Number of pages8
ISBN (Print)9780974903910
DOIs
Publication statusPublished - Jul 2005
Event21st Conference on Uncertainty in Artificial Intelligence, UAI 2005 - Edinburgh, United Kingdom
Duration: 26 Jul 200529 Jul 2005
https://www.auai.org/uai2005/ (Conference website)
https://dl.acm.org/doi/proceedings/10.5555/3020336 (Conference proceedings)

Conference

Conference21st Conference on Uncertainty in Artificial Intelligence, UAI 2005
Country/TerritoryUnited Kingdom
CityEdinburgh
Period26/07/0529/07/05
Internet address

Fingerprint

Dive into the research topics of 'A transformational characterization of Markov equivalence for directed acyclic graphs with latent variables'. Together they form a unique fingerprint.

Cite this