Lifted Probabilistic Inference: An MCMC Perspective

Niepert, Mathias

Preview

PDF
niepert.pdf - Published
Download (624kB)

URL:	https://ub-madoc.bib.uni-mannheim.de/32502
Additional URL:	http://citeseerx.ist.psu.edu/viewdoc/download?doi=...
URN:	urn:nbn:de:bsz:180-madoc-325027
Document Type:	Working paper
Year of publication:	2012
Place of publication:	Mannheim
Publication language:	English
Institution:	School of Business Informatics and Mathematics > Practical Computer Science II: Artificial Intelligence (Stuckenschmidt 2009-)
Subject:	004 Computer science, internet
Abstract:	The general consensus seems to be that lifted inference is concerned with exploiting model symmetries and grouping indistinguishable objects at inference time. Since first-order probabilistic formalisms are essentially tem- plate languages providing a more compact representation of a corresponding ground model, lifted inference tends to work especially well in these models. We show that the notion of indistinguishability manifests itself on several dferent levels {the level of constants, the level of ground atoms (variables), the level of formulas (features), and the level of assignments (possible worlds). We discuss existing work in the MCMC literature on ex- ploiting symmetries on the level of variable assignments and relate it to novel results in lifted MCMC.
Additional information:	Paper pres. at the 2nd International Workshop on Statistical Relational AI : held at the Uncertanty in Artificial Intelligence Conference (UAI 2012), Catalina Island, Calif., August 18, 2012