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:20190916T140000
DTEND;TZID=Europe/Paris:20190916T151500
DTSTAMP:20260713T035513
CREATED:20190627T090506Z
LAST-MODIFIED:20190627T090506Z
UID:12290-1568642400-1568646900@crest.science
SUMMARY:Yuri POLYANSKI (MIT) - "Smoothed Empirical Measures and Entropy Estimation"
DESCRIPTION:\nThe Statistical Seminar: Every Monday at 2:00 pm.\nTime: 2:00 pm – 3:15 pm\nDate: 16th of September 2019\nPlace: Room 3001.\nYuri POLYANSKI (MIT) – “Smoothed Empirical Measures and Entropy Estimation“ \nAbstract: In this talk we discuss behavior of the empirical measure P_n corresponding to iid samples from a distribution P on a d-dimensional space. Let Q_n and Q denote the result of convolving P_n and P\, respectively\, with an isotropic standard Guassian kernel. We discuss convergence of the p-Wasserstein\, KL and other distances between Q_n and Q. Curiously\, for some distances (like 1-Wasserstein) we get parametric 1/sqrt(n) speed of convergence regardless of dimension\, whereas for some other distances (like 2-Wasserstein) the 1/sqrt(n) rate can change to \omega(1/sqrt(n)). We give an if and only if characterization in the class of subgaussian P for the parametric rate. As an application\, we show that differential entropy of Q_n converges to that of Q at parametric rate 1/sqrt(n) regardless of dimension. An estimator of differential entropy of Q\, in turn\, allows us to estimate the input-output mutual information in noisy neural networks. \nJoint work with Ziv Goldfeld\, Kristjan Greenewald and Jonathan Weed.\nOrganizers:\nCristina BUTUCEA\, Alexandre TSYBAKOV\, Julie JOSSE\, Eric MOULINES\, Mathieu ROSENBAUM\nSponsors:\nCREST-CMAP\n \n\n
URL:https://crest.science/event/yuri-polyanski/
CATEGORIES:Statistics
ATTACH;FMTTYPE=:
END:VEVENT
END:VCALENDAR