BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CREST - ECPv5.1.3//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:CREST
X-ORIGINAL-URL:https://crest.science
X-WR-CALDESC:Events for CREST
BEGIN:VTIMEZONE
TZID:Europe/Paris
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:20190331T010000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:20191027T010000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=Europe/Paris:20191106T140000
DTEND;TZID=Europe/Paris:20191106T150000
DTSTAMP:20260815T030451
CREATED:20191030T073101Z
LAST-MODIFIED:20191030T073101Z
UID:12353-1573048800-1573052400@crest.science
SUMMARY:Badr-Eddine CHERIEF-ABDELLATIF(CREST) - "Theoretical Study of Variational Inference"
DESCRIPTION:\nThe Stats-Machine Learning-Econometrics Seminar.\nTime: 14:00 pm – 15:00 pm\nDate: 6th of November 2019\nPlace: Room 3001.\nBadr-Eddine CHERIEF-ABDELLATIF(CREST) – “Theoretical Study of Variational Inference”\n Abstract : Bayesian inference provides an attractive learning framework to analyze and to sequentially update knowledge on streaming data\, but is rarely computationally feasible in practice. In the recent years\, variational inference (VI) has become more and more popular for approximating intractable posterior distributions in Bayesian statistics and machine learning. Nevertheless\, despite 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. First\, we show that variational inference is consistent under mild conditions and retains the same properties than exact Bayesian inference in the batch setting. Then\, we study several online VI algorithms that are inspired from sequential optimization in order to compute the variational approximations in an online fashion. We provide theoretical guarantees by deriving generalization bounds and we present empirical evidence in support of this.\n\n\n\nSponsors:\nCREST\n\n\n
URL:https://crest.science/event/badr-eddine-cherief-abdellatif/
LOCATION:ENSAE Paris\, 5\, avenue Henry Le Chatelier\, 91120 Palaiseau\, France
CATEGORIES:Economics,Statistics
ATTACH;FMTTYPE=:
END:VEVENT
END:VCALENDAR