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:20180325T010000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:20181028T010000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=Europe/Paris:20180627T140000
DTEND;TZID=Europe/Paris:20180627T151500
DTSTAMP:20260713T230033
CREATED:20180608T120540Z
LAST-MODIFIED:20180608T120540Z
UID:12084-1530108000-1530112500@crest.science
SUMMARY:Emtiyaz Khan (Riken\, Tokyo) - "Fast yet Simple Natural-Gradient Variational Inference"
DESCRIPTION:\nThe Statistical Seminar: Every Monday at 2:00 pm.\nTime: 2:00 pm – 3:15 pm\nDate: 27th of June 2018 exceptionally Wednesday\nPlace: Room 3001.\nEmtiyaz Khan (Riken\, Tokyo) – “Fast yet Simple Natural-Gradient Variational Inference in Complex Models“ \nAbstract: Approximate Bayesian inference is promising in improving generalization and reliability of deep learning\, but is computationally challenging. Modern variational-inference (VI) methods circumvent the challenge by formulating Bayesian inference as an optimization problem and then solving it using gradient-based methods. In this talk\, I will argue in favor of natural-gradient approaches which can improve convergence of VI by exploiting the information geometry of the solutions. I will discuss a fast yet simple natural-gradient method obtained by using a duality associated with exponential-family distributions. I will summarize some of our recent results on Bayesian deep learning\, where natural-gradient methods lead to an approach which gives simpler updates than existing VI methods while performing comparably to them. \nOrganizers:\nCristina BUTUCEA\, Alexandre TSYBAKOV\, Eric MOULINES\, Mathieu ROSENBAUM\nSponsors:\nCREST-CMAP\n \n\n
URL:https://crest.science/event/jamal-najim-cnrs-upem-tba-2-2-3-5-2-2-2/
CATEGORIES:Statistics
ATTACH;FMTTYPE=:
END:VEVENT
END:VCALENDAR