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:20190331T010000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:20191027T010000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=Europe/Paris:20191202T140000
DTEND;TZID=Europe/Paris:20191202T151500
DTSTAMP:20210919T143830
CREATED:20191003T093034Z
LAST-MODIFIED:20191003T093034Z
UID:12340-1575295200-1575299700@crest.science
SUMMARY:Henry REEVE (Université de Birmingham) - "Classification with unknown class conditional label noise on non-compact feature spaces "
DESCRIPTION:\nThe Statistical Seminar: Every Monday at 2:00 pm.\nTime: 2:00 pm – 3:15 pm\nDate: 2nd of December 2019\nPlace: Room 3001.\nHenry REEVE (Université de Birmingham) – “Classification with unknown class conditional label noise on non-compact feature spaces“ \nAbstract: We consider the problem of classification in the presence of label noise. In the analysis of classification problems it is typically assumed that the train and test distributions are one and the same. In practice\, however\, it is often the case that the labels in the training data have been corrupted with some unknown probability. We shall focus on classification with class conditional label noise in which the labels observed by the learner have been corrupted with some unknown probability which is determined by the true class label. \nIn order to obtain finite sample rates\, previous approaches to classification with unknown class conditional label noise have required that the regression function attains its extrema uniformly on sets of positive measure. We consider this problem in the setting of non-compact metric spaces\, where the regression function need not attain its extrema. \nIn this setting we determine the minimax optimal learning rates (up to logarithmic factors). The rate displays interesting threshold behaviour: When the regression function approaches its extrema at a sufficient rate\, the optimal learning rates are of the same order as those obtained in the label-noise free setting. If the regression function approaches its extrema more gradually then classification performance necessarily degrades. In addition\, we present an algorithm which attains these rates without prior knowledge of either the distributional parameters or the local density. \nOrganizers:\nCristina BUTUCEA\, Alexandre TSYBAKOV\, Julie JOSSE\, Eric MOULINES\, Mathieu ROSENBAUM\nSponsors:\nCREST-CMAP\n \n\n
URL:https://crest.science/event/henry-reeve/
CATEGORIES:Statistics
ATTACH;FMTTYPE=:
END:VEVENT
END:VCALENDAR