BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//wp-events-plugin.com//7.2.3.1//EN
TZID:Europe/Paris
X-WR-TIMEZONE:Europe/Paris
BEGIN:VEVENT
UID:3134@i2m.univ-amu.fr
DTSTART;TZID=Europe/Paris:20191104T140000
DTEND;TZID=Europe/Paris:20191104T160000
DTSTAMP:20191020T120000Z
URL:https://www.i2m.univ-amu.fr/evenements/badr-eddine-cherief-abdellatif-
 theoretical-study-of-variational-inference-foundations-recent-advances/
SUMMARY: (...): Badr-eddine CHERIEF-ABDELLATIF - Theoretical study of varia
 tional inference: foundations & recent advances
DESCRIPTION:: Badr-eddine CHÉRIEF-ABDELLATIF (CREST-ENSAE\, Paris)Bayesian
  inference provides an attractive learning framework to analyze and to seq
 uentially update knowledge on streaming data\, but is rarely computational
 ly feasible in practice. In the recent years\, variational inference (VI) 
 has become more and more popular for approximating intractable posterior d
 istributions in Bayesian statistics and machine learning. Nevertheless\, d
 espite promising results in real-life applications\, only little attention
  has been put in the literature towards the theoretical properties of VI. 
 In this talk\, we aim to present some recent advances in theory of VI. We 
 will show that variational inference is consistent under mild conditions a
 nd retains the same properties than exact Bayesian inference\, and we will
  present several applications to illustrate our general results. We will a
 lso briefly discuss some extensions of these results.https://badreddineche
 riefabdellatif.github.io
END:VEVENT
BEGIN:VTIMEZONE
TZID:Europe/Paris
X-LIC-LOCATION:Europe/Paris
BEGIN:STANDARD
DTSTART:20191027T020000
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
END:STANDARD
END:VTIMEZONE
END:VCALENDAR