Fullscreen
Loading...
 
Tao
Print

Seminar24102017

October, Tuesday 24th

14:30 (Shannon amphitheatre, building 660) (see location ):

Benjamin Guedj

(MODAL project-team of Inria Lille [MOdels for Data Analysis and Learning] / Laboratoire Paul Painlevé, University of Lille)

Title: A quasi-Bayesian perspective to NMF: theory and applications


Abstract:

Quasi-Bayesian estimators are increasingly popular in statistics and machine learning, due to their generalization properties and flexibility. In a recent work (Alquier & Guedj 2017, Mathematical Methods of Statistics), we have proposed a quasi-Bayesian estimator for non-negative matrix factorization. I will present a quick overview of quasi- and PAC-Bayesian frameworks and discuss our theoretical and algorithmic contributions. A short demo of our method for digits recognition will conclude the talk.

Reference:

http://dx.doi.org/10.3103/S1066530717010045

Website:

https://bguedj.github.io




Contact: guillaume.charpiat at inria.fr


Contributors to this page: guillaume .
Page last modified on Friday 15 of September, 2017 22:14:41 CEST by guillaume.