Markov Logic in Infinite Domains

Authors Pedro Domingos, Parag Singla

Thumbnail PDF


  • Filesize: 199 kB
  • 16 pages

Document Identifiers

Author Details

Pedro Domingos
Parag Singla

Cite AsGet BibTex

Pedro Domingos and Parag Singla. Markov Logic in Infinite Domains. In Probabilistic, Logical and Relational Learning - A Further Synthesis. Dagstuhl Seminar Proceedings, Volume 7161, pp. 1-16, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2008)


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.
  • Markov logic networks
  • Gibbs measures
  • first-order logic
  • infinite probabilistic models
  • Markov networks


  • Access Statistics
  • Total Accesses (updated on a weekly basis)
    PDF Downloads
Questions / Remarks / Feedback

Feedback for Dagstuhl Publishing

Thanks for your feedback!

Feedback submitted

Could not send message

Please try again later or send an E-mail