BEGIN:VCALENDAR
VERSION:2.0
X-WR-CALNAME;VALUE=TEXT:Colloq: Yves Atchade
PRODID:-//Harvard events data//EN
BEGIN:VEVENT
UID:event_1122658_0
SUMMARY:Colloq: Yves Atchade
DESCRIPTION:<p>	<a data-fid="740541" href="internal:/files/statistics/files/yves_atchade_-_october_7th.pdf">Bayesian statistics without likelihood</a></p><p>	Bayesian analysis of high-dimensional graphical models often leads to posterior distributions that are computationally intractable. Similar issues arise with other classes of statistical models. In this talk I will advocate the use of more general loss functions in the Bayesian machinery. The idea is not new, but I will present some new results on the contraction properties of the resulting quasi-posterior distributions in the high-dimensional regime. Computational aspects will also be discussed if time permits.</p>
LOCATION:Science Center Rm. 300H
STATUS:CONFIRMED
DTSTART:20161107T211500Z
DTEND:20161107T221500Z
END:VEVENT
END:VCALENDAR