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:20180528T140000
DTEND;TZID=Europe/Paris:20180528T151500
DTSTAMP:20260715T002200
CREATED:20180504T151131Z
LAST-MODIFIED:20180504T151131Z
UID:12058-1527516000-1527520500@crest.science
SUMMARY:Sivaraman BALAKRISHNAN (Carnegie Mellon University) - "On computationally-efficient robust and non-convex estimation"
DESCRIPTION:\nThe Statistical Seminar: Every Monday at 2:00 pm.\nTime: 2:00 pm – 3:15 pm\nDate: 28th of May 2018\nPlace: Room 3001.\nSivaraman BALAKRISHNAN (Carnegie Mellon University) – “On computationally-efficient robust and non-convex estimation“ \nAbstract: \nClassical statistical estimators have long been understood to be extremely susceptible to outliers and model misspecification\, and this insight led to the development of the field of robust statistics. While statistical issues in robust estimation\, i.e. designing and characterizing optimal estimators\, are mostly well-understood several open questions remain in designing computationally-efficient practical estimators.\nBuilding on recent work\, that provided novel estimators for robust mean estimation\, we provide a new class of computationally-efficient class of estimators for risk minimization that are provably robust in a variety of settings. Our workhorse is a novel robust variant of gradient descent\, and we provide conditions under which our gradient descent variant provides accurate and robust estimators in any general convex risk minimization problem. These results provide some of the first computationally tractable and provably robust estimators for many canonical statistical models.\nIf time permits I will connect some of our recent work on robust parametric estimation to past work on establishing rigorous global convergence guarantees for estimation in latent variable models via non-convex likelihood maximization.\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/
CATEGORIES:Statistics
ATTACH;FMTTYPE=:
END:VEVENT
END:VCALENDAR