BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:The information complexity of sequential resource allocation - Emi
 lie Kaufmann (INRIA LIlle)
DTSTART:20160422T150000Z
DTEND:20160422T160000Z
UID:TALK65792@talks.cam.ac.uk
CONTACT:Quentin Berthet
DESCRIPTION:This talk will be about sequential resource allocation\, under
  the so-called stochastic multi-armed bandit model. In this model\, an age
 nt interacts with a set of (unknown) probability distributions\, called 'a
 rms' (in reference to 'one-armed bandits'\, another name for slot machines
  in a casino). When the agent draws an arm\, he observes a sample from the
  associated distribution. This sample can be seen as a reward\, and the ag
 ent then aims at maximizing the sum of his rewards during the interaction.
  This 'regret minimization' objective makes sense in many practical applic
 ations\, starting with medical trials\, that motivated the introduction of
  bandit problems in the 1930's.  Another possible objective for the agent\
 , called best-arm identification\, is to discover as fast as possible the 
 best arm(s)\, that is the arms whose distributions have highest mean\, but
  without suffering a loss when drawing 'bad' arms. \n \nFor each of these 
 objectives\, our goal will be to define a distribution-dependent notion of
  optimality\, thanks to lower bounds on the performance of good strategies
 \, and to propose algorithms that can be qualified as optimal according to
  these lower bounds. For some classes of parametric bandit models\, this p
 ermits to characterize the complexity of regret minimization and best-arm 
 identification in terms of (different) information-theoretic quantities.
LOCATION:MR12\, Centre for Mathematical Sciences\, Wilberforce Road\, Camb
 ridge.
END:VEVENT
END:VCALENDAR