Calibration of conditional composite likelihood for Bayesian inference on Gibbs random fields - CNRS - Centre national de la recherche scientifique Accéder directement au contenu
N°Spécial De Revue/Special Issue Proceedings of Machine Learning Research Année : 2015

Calibration of conditional composite likelihood for Bayesian inference on Gibbs random fields

Résumé

Gibbs random fields play an important role in statistics, however, the resulting likelihood is typically unavailable due to an intractable normalizing constant. Composite likelihoods offer a principled means to construct useful approximations. This paper provides a mean to calibrate the posterior distribution resulting from using a composite likelihood and illustrate its performance in several examples.
Fichier principal
Vignette du fichier
CompLike_Stoehr_Friel_2015.pdf (378.32 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01108279 , version 1 (22-01-2015)
hal-01108279 , version 2 (06-02-2015)

Identifiants

Citer

Julien Stoehr, Nial Friel. Calibration of conditional composite likelihood for Bayesian inference on Gibbs random fields. The Eighteenth International Conference on Artificial Intelligence and Statistics, May 2015, San Diego, United States. Proceedings of Machine Learning Research, 38, pp.921-929, 2015. ⟨hal-01108279v2⟩
115 Consultations
117 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More