Robust Graphical Modelling with t-Distributions

Michael Finegold, Mathias Drton
Proceedings of the 25th Conference on Uncertainty in Artificial Intelligence, PMLR R7:169-176, 2009.

Abstract

Graphical Gaussian models have proven to be useful tools for exploring network structures based on multivariate data. Applications to studies of gene expression have generated substantial interest in these models, and resulting recent progress includes the development of fitting methodology involving penalization of the likelihood function. In this paper we advocate the use of the multivariate t and related distributions for more robust inference of graphs. In particular, we demonstrate that penalized likelihood inference combined with an application of the EM algorithm provides a simple and computationally efficient approach to model selection in the t-distribution case. 1

Cite this Paper

BibTeX
@InProceedings{pmlr-vR7-finegold09a, title = {Robust Graphical Modelling with t-Distributions}, author = {Finegold, Michael and Drton, Mathias}, booktitle = {Proceedings of the 25th Conference on Uncertainty in Artificial Intelligence}, pages = {169--176}, year = {2009}, editor = {Bilmes, Jeff and Ng, Andrew Y.}, volume = {R7}, series = {Proceedings of Machine Learning Research}, month = {18--21 Jun}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/r7/main/assets/finegold09a/finegold09a.pdf}, url = {https://proceedings.mlr.press/r7/finegold09a.html}, abstract = {Graphical Gaussian models have proven to be useful tools for exploring network structures based on multivariate data. Applications to studies of gene expression have generated substantial interest in these models, and resulting recent progress includes the development of fitting methodology involving penalization of the likelihood function. In this paper we advocate the use of the multivariate t and related distributions for more robust inference of graphs. In particular, we demonstrate that penalized likelihood inference combined with an application of the EM algorithm provides a simple and computationally efficient approach to model selection in the t-distribution case. 1}, note = {Reissued by PMLR on 04 October 2026.} }
Endnote
%0 Conference Paper %T Robust Graphical Modelling with t-Distributions %A Michael Finegold %A Mathias Drton %B Proceedings of the 25th Conference on Uncertainty in Artificial Intelligence %C Proceedings of Machine Learning Research %D 2009 %E Jeff Bilmes %E Andrew Y. Ng %F pmlr-vR7-finegold09a %I PMLR %P 169--176 %U https://proceedings.mlr.press/r7/finegold09a.html %V R7 %X Graphical Gaussian models have proven to be useful tools for exploring network structures based on multivariate data. Applications to studies of gene expression have generated substantial interest in these models, and resulting recent progress includes the development of fitting methodology involving penalization of the likelihood function. In this paper we advocate the use of the multivariate t and related distributions for more robust inference of graphs. In particular, we demonstrate that penalized likelihood inference combined with an application of the EM algorithm provides a simple and computationally efficient approach to model selection in the t-distribution case. 1 %Z Reissued by PMLR on 04 October 2026.
APA
Finegold, M. & Drton, M.. (2009). Robust Graphical Modelling with t-Distributions. Proceedings of the 25th Conference on Uncertainty in Artificial Intelligence, in Proceedings of Machine Learning Research R7:169-176 Available from https://proceedings.mlr.press/r7/finegold09a.html. Reissued by PMLR on 04 October 2026.

Related Material