BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//wp-events-plugin.com//7.2.3.1//EN
TZID:Europe/Paris
X-WR-TIMEZONE:Europe/Paris
BEGIN:VEVENT
UID:2046@i2m.univ-amu.fr
DTSTART;TZID=Europe/Paris:20171204T150000
DTEND;TZID=Europe/Paris:20171204T160000
DTSTAMP:20171119T140000Z
URL:https://www.i2m.univ-amu.fr/evenements/online-nonparametric-regression
 -with-adversarial-data/
SUMMARY: (...): Online nonparametric regression with adversarial data.
DESCRIPTION:: In this talk\, I will consider the problem of online nonparam
 etric regression with arbitrary deterministic sequences. Using ideas from 
 the chaining technique\, I will design an algorithm that achieves a Dudley
 -type regret bound. The algorithm is the first one that achieves optimal r
 ates for online regression over Hölder balls. We will also investigate if
  we can apply the same technique to other problems by changing the feedbac
 k (bandit feedback\,…) or the loss function. 
END:VEVENT
BEGIN:VTIMEZONE
TZID:Europe/Paris
X-LIC-LOCATION:Europe/Paris
BEGIN:STANDARD
DTSTART:20171029T020000
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
END:STANDARD
END:VTIMEZONE
END:VCALENDAR