BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Bandit Optimisation with Large Strategy Sets: Theory and Applicati
 ons - Proutiere\, A (KTH)
DTSTART:20130814T100000Z
DTEND:20130814T104500Z
UID:TALK46639@talks.cam.ac.uk
CONTACT:Mustapha Amrani
DESCRIPTION:In this talk\, we report recent results on bandit optimisation
  problems with large strategy (or decision) sets. These problems naturally
  arise in many contemporary applications found in communication networks\,
  e-commerce\, and recommendation systems. We address both stochastic or ad
 versarial settings\, depending on the way rewards obtained under various s
 trategies are generated. We provide lower bounds on regret\, which provide
  fundamental performance limits that any online algorithm cannot beat\, an
 d develop algorithms that approach these limits. Results are applied to re
 source allocation in wireless networks\, and recommendation systems. \n
LOCATION:Seminar Room 1\, Newton Institute
END:VEVENT
END:VCALENDAR