liu.seSearch for publications in DiVA
Change search
ReferencesLink to record
Permanent link

Direct link
Factorization, Inference and Parameter Learning in Discrete AMP Chain Graphs
Linköping University, Department of Computer and Information Science, Database and information techniques. Linköping University, Faculty of Science & Engineering.
2015 (English)In: SYMBOLIC AND QUANTITATIVE APPROACHES TO REASONING WITH UNCERTAINTY, ECSQARU 2015, SPRINGER-VERLAG BERLIN , 2015, Vol. 9161, 335-345 p.Conference paper (Refereed)Text
Abstract [en]

We address some computational issues that may hinder the use of AMP chain graphs in practice. Specifically, we show how a discrete probability distribution that satisfies all the independencies represented by an AMP chain graph factorizes according to it. We show how this factorization makes it possible to perform inference and parameter learning efficiently, by adapting existing algorithms for Markov and Bayesian networks. Finally, we turn our attention to another issue that may hinder the use of AMP CGs, namely the lack of an intuitive interpretation of their edges. We provide one such interpretation.

Place, publisher, year, edition, pages
SPRINGER-VERLAG BERLIN , 2015. Vol. 9161, 335-345 p.
Series
Lecture Notes in Computer Science, ISSN 0302-9743 (print), 1611-3349 (online) ; 9161
National Category
Computer and Information Science
Identifiers
URN: urn:nbn:se:liu:diva-123538DOI: 10.1007/978-3-319-20807-7_30ISI: 000364847800030ISBN: 978-3-319-20807-7; 978-3-319-20806-0OAI: oai:DiVA.org:liu-123538DiVA: diva2:886129
Conference
13th European Conference on Symbolic and Quantitative Approaches to Reasoning with Uncertainty (ECSQARU)
Available from: 2015-12-21 Created: 2015-12-21 Last updated: 2015-12-21

Open Access in DiVA

No full text

Other links

Publisher's full text

Search in DiVA

By author/editor
Pena, Jose M
By organisation
Database and information techniquesFaculty of Science & Engineering
Computer and Information Science

Search outside of DiVA

GoogleGoogle Scholar
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Altmetric score

Total: 30 hits
ReferencesLink to record
Permanent link

Direct link