BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Moment matching for latent variable models: from ICA to LDA and CC
 A - Professor Francis Bach (INRIA\, ENS)
DTSTART:20161006T100000Z
DTEND:20161006T110000Z
UID:TALK68096@talks.cam.ac.uk
CONTACT:Zoubin Ghahramani
DESCRIPTION:Moment matching is a traditional alternative to maximum likeli
 hood for parameter estimation in probabilistic models. For certain latent 
 variable models\, this has recently led to parameter estimation algorithms
  with theoretical guarantees. While independent component analysis (ICA) w
 as the first semi-parametric model to be considered twenty years ago\, thi
 s has been recently extended to latent Dirichlet Allocation (LDA)\, which 
 is a parametric model for discrete data. In this talk I will present (a) a
  semi-parametric extension of LDA which\, beyond making fewer modelling as
 sumptions\, leads to simpler estimation through moment matching techniques
 \, and (b) an extension to multi-view models such as canonical correlation
  analysis (CCA). (Joint work with Anastasia Podosinnikova and Simon Lacost
 e-Julien).
LOCATION:CBL Room BE-438
END:VEVENT
END:VCALENDAR