Learning AMP Chain Graphs under Faithfulness
2012 (English)Conference paper (Other academic)
This paper deals with chain graphs under the alternative Andersson-Madigan-Perlman(AMP) interpretation. In particular, we present a constraint based algorithm for learningan AMP chain graph a given probability distribution is faithful to. We also show that theextension of Meek's conjecture to AMP chain graphs does not hold, which compromises thedevelopment of ecient and correct score+search learning algorithms under assumptionsweaker than faithfulness.
Place, publisher, year, edition, pages
2012. 251-258 p.
, Sixth European Workshop on Probabilistic Graphical Models (PGM 2012), ISSN 978-84-15536-57-4
IdentifiersURN: urn:nbn:se:liu:diva-80305OAI: oai:DiVA.org:liu-80305DiVA: diva2:546465
Sixth European Workshop on Probabilistic Graphical Models (PGM 2012), 19-21 September 2012, Granada, Spain