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/Helsinki
BEGIN:DAYLIGHT
TZOFFSETFROM:+0200
TZOFFSETTO:+0300
TZNAME:EEST
DTSTART:20230326T010000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0300
TZOFFSETTO:+0200
TZNAME:EET
DTSTART:20231029T010000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=Europe/Helsinki:20230925T140000
DTEND;TZID=Europe/Helsinki:20230925T151500
DTSTAMP:20260723T125523
CREATED:20230912T113316Z
LAST-MODIFIED:20230912T113316Z
UID:15448-1695650400-1695654900@crest.science
SUMMARY:Hannes LEEB (Vienna University) - Conditional Predictive Inference for Stable Algorithms
DESCRIPTION:Statistical Seminar: Every Monday at 2:00 pm.\nTime: 2:00 pm – 3:15 pm\nDate: 25th September 2023\nPlace : \n  \nHannes LEEB – Conditional Predictive Inference for Stable Algorithms \n  \nAbstract: \n  \nWe investigate generically applicable and intuitively appealing prediction intervals based on k-fold cross-validation. We focus on the conditional coverage probability of the proposed intervals\, given the observations in the training sample (hence\, training conditional validity)\, and show that it is close to the nominal level\, in an appropriate sense\, provided that the underlying\nalgorithm used for computing point predictions is sufficiently stable when feature-response pairs are omitted. Our results are based on a finite sample analysis of the empirical distribution function of k-fold cross-validation residuals and hold in nonparametric settings with only minimal assumptions on the error distribution. To illustrate our results\, we also apply them to high-dimensional linear predictors\, where we obtain uniform asymptotic training conditional validity as both sample size and dimension tend to infinity at the same rate and consistent parameter estimation typically fails. These results show that despite the serious problems of resampling procedures for inference on the unknown parameters\, cross-validation methods can be successfully applied to obtain reliable predictive inference\neven in high dimensions and conditionally on the training data. \n  \n  \nOrganizers:\nCristina BUTUCEA (CREST)\, Alexandre TSYBAKOV (CREST)\, Karim LOUNICI (CMAP) \, Jaouad MOURTADA (CREST)\nSponsors:\nCREST-CMAP \n
URL:https://crest.science/event/hannes-leeb-vienna-university-conditional-predictive-inference-for-stable-algorithms/
CATEGORIES:Statistics
ATTACH;FMTTYPE=:
END:VEVENT
END:VCALENDAR