BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CREST - ECPv5.1.4//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:20200921T140000
DTEND;TZID=Europe/Paris:20200921T151500
DTSTAMP:20201129T045755
CREATED:20200915T100442Z
LAST-MODIFIED:20200915T100456Z
UID:10484-1600696800-1600701300@crest.science
SUMMARY:Jaouad MOURTADA (CREST) - " Statistical leverage in prediction: from least squares to logistic regression "
DESCRIPTION:\nThe Statistical Seminar: Every Monday at 2:00 pm. \nTime: 2:00 pm – 3:15 pm\nDate: 21th of september 2020\nPlace: Visio \nJaouad MOURTADA (CREST) – “Statistical leverage in prediction: from least squares to logistic regression” \nAbstract: We consider statistical learning/prediction problems: based on an iid sample\, one aims to find a good predictor of a response given some features. In this context\, an input sample has high leverage (relative to some learning algorithm or class of predictors) if the prediction at this point is sensitive to the associated output. \nIn the context of random-design linear prediction with square loss\, we show that the hardness of the problem is characterized by the distribution of leverage scores of feature points. As an application\, in high dimension Gaussian design (with nearly constant leverage) is seen to be nearly most favorable through lower bounds on the minimax risk\, as well as refinements depending on the signal-to-noise ratio. \nWe then turn to conditional density estimation with entropy risk. We study this problem in a statistical learning framework\, where given a class of conditional densities (a model)\, the goal is to find estimators that predict almost as well as the best distribution in the model\, without restrictive assumptions on the true distribution. We introduce a new estimator\, given by the solution of some min-max problem involving ‘virtual’ samples\, which quantifies uncertainty according to a notion of leverage. In the case of logistic regression\, this procedure achieves fast learning rates under weak assumptions\, improving over within-model estimators such as regularized MLE; it also admits a simple form and does not require posterior sampling\, providing a computationally less demanding alternative to Bayesian approaches. \nOrganizers:\nCristina BUTUCEA (CREST)\, Alexandre TSYBAKOV (CREST)\, Karim LOUNICI (CMAP) \, Zoltan SZABO (CMAP) \nSponsors:\nCREST-CMAP \n \n\n
URL:https://crest.science/event/jaouad-mourtada
CATEGORIES:Statistics
ATTACH;FMTTYPE=:
END:VEVENT
END:VCALENDAR