BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Solving pure exploration problems with the Top Two approach
DTSTART:20240219T131500
DTEND:20240219T131500
DTSTAMP:20260406T142552Z
UID:cb303a82fa8cbdbe0bda8d76962aef4a7cdf5a302ed86711cf8465bb
CATEGORIES:Conferences - Seminars
DESCRIPTION:Marc Jourdan (INRIA Lille)\n In pure exploration problems for
  stochastic multi-armed bandits\, the goal is to answer a question about a
  set of unknown distributions (modeling for example the efficacy of a trea
 tment) from which we can collect samples (measure its effect)\, and to pro
 vide guarantees on the candidate answer. The archetypal example is the bes
 t arm identification problem\, in which the agent aims at identifying the 
 arm with the highest mean. In this talk\, I will focus on the class of Top
  Two algorithms\, which select the next arm to sample from among two candi
 date arms\, a leader and a challenger. Due to their simplicity and interpr
 etability\, Top Two algorithms have received increased attention in recent
  years. In the fixed-confidence setting\, Top Two algorithms have an asymp
 totically optimal expected sample complexity (number of collected samples 
 when the error level vanishes). In the anytime setting\, we propose a Top 
 Two algorithm which has guarantees on the probability of misidentifying a 
 good enough arm at any time.
LOCATION:GA 3 21 https://plan.epfl.ch/?room==GA%203%2021
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR