Schloss Dagstuhl - Leibniz-Zentrum für Informatik GmbH Schloss Dagstuhl - Leibniz-Zentrum für Informatik GmbH scholarly article en Domingos, Pedro; Singla, Parag License
when quoting this document, please refer to the following
DOI:
URN: urn:nbn:de:0030-drops-13811
URL:

;

Markov Logic in Infinite Domains

pdf-format:


Abstract

Markov logic combines logic and probability by attaching weights to
first-order formulas, and viewing them as templates for features of Markov
networks. Unfortunately, in its original formulation it does not have the
full power of first-order logic, because it applies only to finite domains.
Recently, we have extended Markov logic to infinite domains, by casting it
in the framework of Gibbs measures. In this talk I will summarize our main
results to date, including sufficient conditions for the existence and
uniqueness of a Gibbs measure consistent with an infinite MLN, and
properties of the set of consistent measures in the non-unique case.
(Many important phenomena, like phase transitions, are modeled by
non-unique MLNs.) Under the conditions for existence, we have extended
to infinite domains the result in Richardson and Domingos (2006) that
first-order logic is the limiting case of Markov logic when all weights
tend to infinity. I will also discuss some fundamental limitations of
Herbrand interpretations (and representations based on them) for
probabilistic modeling of infinite domains, and how to get around them.
Finally, I will discuss some of the surprising insights for learning
and inference in large finite domains that result from considering the
infinite limit.



BibTeX - Entry

@InProceedings{domingos_et_al:DagSemProc.07161.6,
  author =	{Domingos, Pedro and Singla, Parag},
  title =	{{Markov Logic in Infinite Domains}},
  booktitle =	{Probabilistic, Logical and Relational Learning - A Further Synthesis},
  pages =	{1--16},
  series =	{Dagstuhl Seminar Proceedings (DagSemProc)},
  ISSN =	{1862-4405},
  year =	{2008},
  volume =	{7161},
  editor =	{Luc de Raedt and Thomas Dietterich and Lise Getoor and Kristian Kersting and Stephen H. Muggleton},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/opus/volltexte/2008/1381},
  URN =		{urn:nbn:de:0030-drops-13811},
  doi =		{10.4230/DagSemProc.07161.6},
  annote =	{Keywords: Markov logic networks, Gibbs measures, first-order logic, infinite probabilistic models, Markov networks}
}

Keywords: Markov logic networks, Gibbs measures, first-order logic, infinite probabilistic models, Markov networks
Seminar: 07161 - Probabilistic, Logical and Relational Learning - A Further Synthesis
Issue date: 2008
Date of publication: 06.03.2008


DROPS-Home | Fulltext Search | Imprint | Privacy Published by LZI