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:20220327T010000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0300
TZOFFSETTO:+0200
TZNAME:EET
DTSTART:20221030T010000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=Europe/Helsinki:20220509T140000
DTEND;TZID=Europe/Helsinki:20220509T151500
DTSTAMP:20221209T184330
CREATED:20211020T063620Z
LAST-MODIFIED:20220503T064152Z
UID:13070-1652104800-1652109300@crest.science
SUMMARY:Philippe Rigollet (MIT) - "Variational inference via Wasserstein gradient flows"
DESCRIPTION:Statistical Seminar: Every Monday at 2:00 pm.\nTime: 2:00 pm – 3:15 pm\nDate: 9th of May 2022\nPlace: Amphi 200 \nPhilippe RIGOLLET (MIT) – “Variational inference via Wasserstein gradient flows” \nAbstract: Bayesian methodology typically generates a high-dimensional posterior distribution that is known only up to normalizing constants\, making the computation even of simple summary statistics such as mean and covariance a major computational hurdle. Along with Monte Carlo Markov Chains (MCMC)\, Variational Inference (VI) has emerged as a central computational approach to large-scale Bayesian inference. Rather than sampling from the true posterior\, VI aims at producing a simple but good approximation of the target posterior for which summary statistics are easy to compute. However\, unlike MCMC theory\, which is well-developed and builds on now-classical probabilistic ideas\, VI is still poorly understood and dominated by heuristics. In this work\, we propose a principled method for VI that builds upon the theory of gradient flows on the Bures-Wasserstein space of Gaussian measures. Akin to MCMC\, it comes with theoretical guarantees when the target measure is strongly log-concave. \nThis joint work with Francis Bach\, Silvère Bonnabel\, Sinho Chewi\, and Marc Lambert. \nOrganizers:\nCristina BUTUCEA (CREST)\, Alexandre TSYBAKOV (CREST)\, Karim LOUNICI (CMAP) \, Jaouad MOURTADA (CREST)\nSponsors:\nCREST-CMAP \n
URL:https://crest.science/event/philippe-rigollet-mit-tba/
CATEGORIES:Statistics
ATTACH;FMTTYPE=:
END:VEVENT
END:VCALENDAR