[Statlist] Research seminar in statistics October 30th 2015, GSEM University of Geneva

[Eva Cantoni]

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

Friday October 30th, 2015 at 11h15 - Room M 5220, Uni Mail (40, bd du 
Pont-d'Arve)

Expectation Propagation is exact in the large data limit
Guillaume Dehaene, Neurosciences, UNIGE

ABSTRACT:
Expectation Propagation (EP, Minka 2001) is a popular algorithm for 
approximating posterior distributions. While it is known empirically to 
give good approximations at a low computational cost (Nickisch and 
Rasmussen, 2008), it's also very poorly understood. In this talk, I will 
present some new results on EP in the large-data limit. I will show that 
Gaussian-EP iterations asymptotically behave like the Newton algorithm, 
from which it follows that Gaussian-EP is asymptotically exact. I will 
then give an upper bound on the errors of the EP approximation and show 
that their decay speed compares favorably to the errors of the Laplace 
approximation of the posterior.

These theoretical results can be used to inform practical use of EP, and 
I will give some advice for implementation of the method.


Visit the website: http://www.stat-center.unige.ch/ressem.html


Karen Longden Roure
Program Coordinator
MSc. in Management, MSc. in Economics, MSc. in Statistics
Université de Genève, Uni-Mail
Faculté d'Economie & Management, GSEM
40, bd. du Pont d'Arve, 1211 Genève 4
Tél:  +41.22.379.8109 (10h-14h)


-- 
Prof. Eva Cantoni
Research Center for Statistics and
  Geneva School of Economics and Management
University of Geneva, Bd du Pont d'Arve 40, CH-1211 Genève 4
gsem.unige.ch/rcs/cantoni