BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//wp-events-plugin.com//7.4.0.1//EN
TZID:Europe/Paris
X-WR-TIMEZONE:Europe/Paris
BEGIN:VEVENT
UID:344@isdm.umontpellier.fr
DTSTART;TZID=Europe/Paris:20231204T140000
DTEND;TZID=Europe/Paris:20231204T140000
DTSTAMP:20260828T084834Z
URL:https://isdm.umontpellier.fr/events/multi-armed-bandits-with-guarantee
 d-revenue-per-arm/
SUMMARY:Multi-armed bandits with guaranteed revenue per arm
DESCRIPTION:Room 02.124\, Building 5\, St Priest campus\n\nMachine Learning
  in Montpellier\, Theory &amp\; Practice\n\nWe consider a Multi-Armed Band
 it problem with covering constraints\, where the primary goal is to ensure
  that each arm receives a minimum expected reward while maximizing the tot
 al cumulative reward. In this scenario\, the optimal policy then belongs t
 o some unknown feasible set. Unlike much of the existing literature\, we d
 o not assume the presence of a safe policy or a feasibility margin\, which
  hinders the exclusive use of conservative approaches. Consequently\, we p
 ropose and analyze an algorithm that switches between pessimism and optimi
 sm in the face of uncertainty. We prove both precise problem-dependent and
  problem-independent bounds\, demonstrating that our algorithm achieves th
 e best of the two approaches– depending on the presence or absence of a 
 feasibility margin – in terms of constraint violation guarantees. Furthe
 rmore\, our results indicate that playing greedily on the constraints actu
 ally outperforms pessimism when considering long-term violations rather th
 an violations on a per-round basis. Le jeudi 30 novembre 2023 à 10:22:44 
 UTC+1\, clairemarine.parodi@gmail.com a écrit : Dear all\, On Monday\, De
 cember 4 \, at 2 pm Paris time we will have the following talk: - Dorian B
 audry will give a talk entitled Multi-armed bandits with guaranteed revenu
 e per arm You can join the talk on this link: [ https://isdm.umontpellier.
 fr/inria.webex.com/inria/j.php?MTID=m0d098926b482a7f3e957eab08dc706d3 | ht
 tps://isdm.umontpellier.fr/inria.webex.com/inria/j.php?MTID=m0d098926b482a
 7f3e957eab08dc706d3 ]\n\nMachine Learning in Montpellier\, Theory &amp\; P
 ractice
ATTACH;FMTTYPE=image/jpeg:https://isdm.umontpellier.fr/wp-content/uploads/
 2026/06/ml-mtp-gC78d5.png
CATEGORIES:ML MTP
LOCATION:Saint Priest Campus - Building 5 - Room 02.124\, 860 rue St Priest
 \, Montpellier\, 
X-APPLE-STRUCTURED-LOCATION;VALUE=URI;X-ADDRESS=860 rue St Priest\, Montpel
 lier\, ;X-APPLE-RADIUS=100;X-TITLE=Saint Priest Campus - Building 5 - Room
  02.124:geo:0,0
END:VEVENT
BEGIN:VTIMEZONE
TZID:Europe/Paris
X-LIC-LOCATION:Europe/Paris
BEGIN:STANDARD
DTSTART:20231029T020000
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
END:STANDARD
END:VTIMEZONE
END:VCALENDAR