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:20200329T010000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:20201025T010000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=Europe/Paris:20200210T140000
DTEND;TZID=Europe/Paris:20200210T151500
DTSTAMP:20260712T232003
CREATED:20191203T124114Z
LAST-MODIFIED:20191203T124114Z
UID:12365-1581343200-1581347700@crest.science
SUMMARY:Gilles BLANCHARD (Université Paris Sud) - "Is adaptive early stopping possible in statistical inverse problems?"
DESCRIPTION:\nThe Statistical Seminar: Every Monday at 2:00 pm.\nTime: 2:00 pm – 3:15 pm\nDate: 10th of February 2020\nPlace: Room 3001.\nGilles BLANCHARD (Université Paris Sud)- “Is adaptive early stopping possible in statistical inverse problems? “ \nAbstract: \nConsider a statistical inverse problem where different estimators $\hat{f}_1\, \ldots \, \hat{f}_K$ are available (ranked in order of increasing “complexity”\, here identified with variance) and the classical problem of estimator selection. For a (data-dependent) choice of the estimator index $\hat{k}$\, there exist a number of well-known methods achieving oracle adaptivity in a wide range of contexts\, for instance penalization methods\, or Lepski’s method.\nHowever\, they have in common that the estimators for {\em all} possible values of $k$ have to be computed first\, and only then compared to each other in some way to determine the final choice. Contrast this to an “early stopping” approach where we are able to compute iteratively the estimators for $k= 1\, 2\, \ldots $ and have to decide to stop at some point without being allowed to compute the following estimators. Is oracle adaptivity possible then? This question is motivated by settings where computing estimators for larger $k$ requires more computational cost; furthermore\, some form of early stopping is most often used in practice.\nWe propose a precise mathematical formulation of this question — in the idealized framework of a Gaussian sequence model with $D$ observed noisy coefficients. In this model\, we provide upper and lower bounds on what is achievable using linear regularized filter estimators commonly used for statistical inverse problems.\nJoint work with M. Hoffmann and M. Reiss.\nOrganizers:\nCristina BUTUCEA\, Alexandre TSYBAKOV\, Julie JOSSE\, Eric MOULINES\, Mathieu ROSENBAUM\nSponsors:\nCREST-CMAP\n \n\n
URL:https://crest.science/event/gilles-blanchard/
CATEGORIES:Statistics
ATTACH;FMTTYPE=:
END:VEVENT
END:VCALENDAR