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:20170326T010000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:20171029T010000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=Europe/Paris:20171023T140000
DTEND;TZID=Europe/Paris:20171023T151500
DTSTAMP:20211202T132131
CREATED:20170927T154250Z
LAST-MODIFIED:20170927T154250Z
UID:11931-1508767200-1508771700@crest.science
SUMMARY:ANNULE - Philip THOMPSON (ENSAE-ParisTech CREST) - "Stochastic approximation with heavier tails "
DESCRIPTION:\nThe Statistical Seminar: Every Monday at 2:00 pm.\nTime: 2:00 pm – 3:15 pm\nDate: 23th of October 2017\nPlace: Room 3001.\nPhilipp THOMPSON (ENSAE-ParisTech CREST) “Stochastic approximation with heavier tails “ \nAbstract: We consider the solution of convex optimization and variational inequality problems via the stochastic approximation methodology where the gradient or operator can only be accessed through an unbiased stochastic oracle. First\, we show that (non-asymptotic) convergence is possible with unbounded constraints and a “multiplicative noise” model: the oracle is Lipschitz continuous with a finite pointwise variance which may not be uniformly bounded (as classically assumed). In this setting\, our bounds depend on local variances at solutions and the method uses noise reduction in an efficient manner: given a precision\, it respects a near-optimal sample and averaging complexities of Polyak-Ruppert’s method but attains the order of the (faster) deterministic iteration complexity. Second\, we discuss a more “robust” version where the Lipschitz constant L is unknown but\, in terms of error precision\, near-optimal complexities are maintained. A price to pay when L is unknown is that a large sample regime is assumed (still respecting the complexity of the SAA estimator) and “non-martingale-like” dependencies are introduced. These dependencies are coped with an “iterative localization” argument based on empirical process theory and self-normalization. \nJoint work with A. Iusem (IMPA)\, A. Jofré (CMM-Chile) and R.I. Oliveira (IMPA). \nOrganizers:\nCristina BUTUCEA\, Alexandre TSYBAKOV\, Eric MOULINES\, Mathieu ROSENBAUM\nSponsors:\nCREST-CMAP\n \n\n
URL:https://crest.science/event/philip-thompson-ensae-paristech-crest-stochastic-approximation-with-heavier-tails/
CATEGORIES:Statistics
ATTACH;FMTTYPE=:
END:VEVENT
END:VCALENDAR