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:20220327T010000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0300
TZOFFSETTO:+0200
TZNAME:EET
DTSTART:20221030T010000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=Europe/Helsinki:20220905T140000
DTEND;TZID=Europe/Helsinki:20220905T151500
DTSTAMP:20221209T194551
CREATED:20220826T095037Z
LAST-MODIFIED:20220826T095037Z
UID:13960-1662386400-1662390900@crest.science
SUMMARY:Blair Bilodeau (University of Toronto) "Minimax Rates for Conditional Density Estimation via Empirical Entropy"
DESCRIPTION:Statistical Seminar: Every Monday at 2:00 pm.\nTime: 2:00 pm – 3:15 pm\nDate: 5th of September 2022\nPlace: Visio \nBlair Bilodeau (University of Toronto) “Minimax Rates for Conditional Density Estimation via Empirical Entropy” \nAbstract:We consider the task of estimating a conditional density using i.i.d. samples from a joint distribution\, which is a fundamental problem with applications in both classification and uncertainty quantification for regression. For joint density estimation\, minimax rates have been characterized for general density classes in terms of uniform (metric) entropy\, a well-studied notion of statistical capacity. When applying these results to conditional density estimation\, the use of uniform entropy—which is infinite when the covariate space is unbounded and suffers from the curse of dimensionality—can lead to suboptimal rates. Consequently\, minimax rates for conditional density estimation cannot be characterized using these classical results. We resolve this problem for well-specified models\, obtaining matching (within logarithmic factors) upper and lower bounds on the minimax Kullback–Leibler risk in terms of the empirical Hellinger entropy for the conditional density class. The use of empirical entropy allows us to appeal to concentration arguments based on local Rademacher complexity\, which—in contrast to uniform entropy—leads to matching rates for large\, potentially nonparametric classes and captures the correct dependence on the complexity of the covariate space. Our results require only that the conditional densities are bounded above\, and do not require that they are bounded below or otherwise satisfy any tail conditions. Based on https://arxiv.org/abs/2109.10461. \n \nOrganizers:\nCristina BUTUCEA (CREST)\, Alexandre TSYBAKOV (CREST)\, Karim LOUNICI (CMAP) \, Jaouad MOURTADA (CREST)\nSponsors:\nCREST-CMAP \n
URL:https://crest.science/event/blair-bilodeau-university-of-toronto-minimax-rates-for-conditional-density-estimation-via-empirical-entropy/
CATEGORIES:Statistics
ATTACH;FMTTYPE=:
END:VEVENT
END:VCALENDAR