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

Julien Stoehr, Nial Friel
Proceedings of the Eighteenth International Conference on Artificial Intelligence and Statistics, PMLR 38:921-929, 2015.

Abstract

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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v38-stoehr15, title = {{Calibration of conditional composite likelihood for Bayesian inference on Gibbs random fields}}, author = {Stoehr, Julien and Friel, Nial}, booktitle = {Proceedings of the Eighteenth International Conference on Artificial Intelligence and Statistics}, pages = {921--929}, year = {2015}, editor = {Lebanon, Guy and Vishwanathan, S. V. N.}, volume = {38}, series = {Proceedings of Machine Learning Research}, address = {San Diego, California, USA}, month = {09--12 May}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v38/stoehr15.pdf}, url = {https://proceedings.mlr.press/v38/stoehr15.html}, abstract = {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.} }
Endnote
%0 Conference Paper %T Calibration of conditional composite likelihood for Bayesian inference on Gibbs random fields %A Julien Stoehr %A Nial Friel %B Proceedings of the Eighteenth International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2015 %E Guy Lebanon %E S. V. N. Vishwanathan %F pmlr-v38-stoehr15 %I PMLR %P 921--929 %U https://proceedings.mlr.press/v38/stoehr15.html %V 38 %X 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.
RIS
TY - CPAPER TI - Calibration of conditional composite likelihood for Bayesian inference on Gibbs random fields AU - Julien Stoehr AU - Nial Friel BT - Proceedings of the Eighteenth International Conference on Artificial Intelligence and Statistics DA - 2015/02/21 ED - Guy Lebanon ED - S. V. N. Vishwanathan ID - pmlr-v38-stoehr15 PB - PMLR DP - Proceedings of Machine Learning Research VL - 38 SP - 921 EP - 929 L1 - http://proceedings.mlr.press/v38/stoehr15.pdf UR - https://proceedings.mlr.press/v38/stoehr15.html AB - 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. ER -
APA
Stoehr, J. & Friel, N.. (2015). Calibration of conditional composite likelihood for Bayesian inference on Gibbs random fields. Proceedings of the Eighteenth International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 38:921-929 Available from https://proceedings.mlr.press/v38/stoehr15.html.

Related Material