[Statlist] Research Webinar in Statistics *FRIDAY, 13 NOVEMBER 2020* GSEM, University of Geneva

gsem-support-instituts g@em-@upport-|n@t|tut@ @end|ng |rom un|ge@ch
Mon Nov 9 08:40:26 CET 2020


Dear All,

We are pleased to invite you to our next Research Webinar.

Looking forward to seeing you


Organizers :                                                                                   
E. Cantoni - S. Engelke - D. La Vecchia - E. Ronchetti
S. Sperlich - F. Trojani - M.-P. Victoria-Feser


FRIDAY, 13 NOVEMBER 2020 at 11:15am
ONLINE
Please join the Zoom research webinar: https://unige.zoom.us/j/99238951053?pwd=dkd5UlRlYXkvNzZicnY0UlBCeW5rdz09
Password: 419459


Modelling with Positive Dependence: Graphical Models, and Convex Optimization
(joint with Steffen Lauritzen and Caroline Uhler)
Piotr ZWIERNIK (http://www.econ.upf.edu/~piotr/) - Universitat Pompeu Fabra & Barcelona Graduate School of Economics, Spain

ABSTRACT:
Probability distributions that are multivariate totally positive of order 2 (MTP2) appeared in the theory of positive dependence and in statistical physics through the celebrated FKG inequality. The MTP2 property is stable under marginalization, conditioning and it appears naturally in various probabilistic graphical models with hidden variables. Models of exponential families with the MTP2 property admit a unique maximum likelihood estimator. In the Gaussian case, the MLE exists also in high-dimensional settings, when p>n, and it leads to sparse solutions. The main aim of this lecture is to give a high-level idea of what the MTP2 condition is as well as to show how total positivity becomes useful in statistical modelling.  I will conclude the presentation showing a particularly tractable relaxation of the MTP2 property and present the GOLAZO algorithm which offers a flexible approach for learning sparsity in Gaussian distributions that takes into account positive dependence.


Visit the website: https://www.unige.ch/gsem/en/research/seminars/rcs/

-------------- next part --------------
A non-text attachment was scrubbed...
Name: RCS_Seminar_Zwiernik.pdf
Type: application/pdf
Size: 179180 bytes
Desc: RCS_Seminar_Zwiernik.pdf
URL: <https://stat.ethz.ch/pipermail/statlist/attachments/20201109/b9a40c0f/attachment.pdf>


More information about the Statlist mailing list