BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Online nonparametric regression with adversarial data - Pierre Gai
 llard (INRIA Paris)
DTSTART:20171027T150000Z
DTEND:20171027T160000Z
UID:TALK87051@talks.cam.ac.uk
CONTACT:Quentin Berthet
DESCRIPTION:In this talk\, I will consider the problem of online nonparame
 tric regression with arbitrary deterministic sequences. Using ideas from t
 he chaining technique\, I will design an algorithm that achieves a Dudley-
 type regret bound similar to the one obtained in a non-constructive fashio
 n by Rakhlin and Sridharan (2014). The regret bound is expressed in terms 
 of the metric entropy in the sup norm\, which yields optimal guarantees wh
 en the metric and sequential entropies are of the same order of magnitude.
  In particular the algorithm is the first one that achieves optimal rates 
 for online regression over Hölder balls.
LOCATION:MR12
END:VEVENT
END:VCALENDAR