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/Helsinki
BEGIN:DAYLIGHT
TZOFFSETFROM:+0200
TZOFFSETTO:+0300
TZNAME:EEST
DTSTART:20200329T010000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0300
TZOFFSETTO:+0200
TZNAME:EET
DTSTART:20201025T010000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=Europe/Helsinki:20200914T140000
DTEND;TZID=Europe/Helsinki:20200914T151500
DTSTAMP:20260712T135929
CREATED:20200907T072300Z
LAST-MODIFIED:20200907T072300Z
UID:12444-1600092000-1600096500@crest.science
SUMMARY:Anna KORBA (CREST) - " A Non Asymptotic Analysis of Stein Variational Gradient Descent  "
DESCRIPTION:\nThe Statistical Seminar: Every Monday at 2:00 pm.\nTime: 2:00 pm – 3:15 pm\nDate: 14th of september 2020\nPlace: Visio\nAnna KORBA (CREST) – “A Non Asymptotic Analysis of Stein Variational Gradient Descent  “ \nAbstract: We study the Stein Variational Gradient Descent (SVGD) algorithm\, which optimises a set of particles to approximate a target probability distribution π∝e−V on ℝd. In the population limit\, SVGD performs gradient descent in the space of probability distributions on the KL divergence with respect to π\, where the gradient is smoothed through a kernel integral operator. In this paper\, we provide a novel finite time analysis for the SVGD algorithm. \nWe provide a descent lemma establishing that the algorithm decreases the objective at each iteration\, and rates of convergence.\nWe also provide a convergence result of the finite particle system corresponding to the practical implementation of SVGD to its population version.\n \n \nOrganizers:\nCristina BUTUCEA (CREST)\, Alexandre TSYBAKOV (CREST)\, Karim LOUNICI (CMAP) \, Zoltan SZABO (CMAP)\nSponsors:\nCREST-CMAP\n \n\n
URL:https://crest.science/event/anna-korba/
CATEGORIES:Statistics
ATTACH;FMTTYPE=:
END:VEVENT
END:VCALENDAR