Institutional tag:
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.
Dates:
Friday, March 24, 2017 - 11:00
Location:
Inria, room A00
Speaker(s):
Benjamin Guedj
Affiliation(s):
Inria MODAL
Speaker's URL:
Presented work's URL: