BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CREST - ECPv5.1.3//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:CREST
X-ORIGINAL-URL:https://crest.science
X-WR-CALDESC:Events for CREST
BEGIN:VTIMEZONE
TZID:Europe/Helsinki
BEGIN:DAYLIGHT
TZOFFSETFROM:+0200
TZOFFSETTO:+0300
TZNAME:EEST
DTSTART:20250330T010000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0300
TZOFFSETTO:+0200
TZNAME:EET
DTSTART:20251026T010000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=Europe/Helsinki:20250120T140000
DTEND;TZID=Europe/Helsinki:20250120T153000
DTSTAMP:20260710T102603
CREATED:20250113T092701Z
LAST-MODIFIED:20250113T092714Z
UID:17755-1737381600-1737387000@crest.science
SUMMARY:Evgenii CHZHEN (CNRS\, Université Paris-Saclay) - Small total-cost constraints in contextual bandits with knapsacks (with some applications to fairness)
DESCRIPTION:Statistical Seminar: Every Monday at 2:00 pm.\nTime: 2:00 pm – 3:00 pm\nDate: 20th January\nPlace: 3001 \n  \nEvgenii Chzhen (CNRS\, Université Paris-Saclay) – Small total-cost constraints in contextual bandits with knapsacks (with some applications to fairness) \n  \n Abstract:  \nI will talks about some recent developments in the literature of contextual bandit problems with knapsacks [CBwK]\, a problem where at each round\, a scalar reward is obtained and vector-valued costs are suffered. The goal is to maximize the cumulative rewards while ensuring that the cumulative costs are lower than some predetermined cost constraints. In this setting\, total cost constraints had so far to be at least of order T^{3/4} where T is the number of rounds\, and were even typically assumed to depend linearly on T. Elaborating on the main technical challenges and drawbacks of previous approaches\, I will present a dual strategy based on projected-gradient-descent updates\, that is able to deal with total-cost constraints of the order of T^{1/2} up to poly-logarithmic terms. This strategy is direct\, and it relies on a careful\, adaptive\, tuning of the step size. The approach is inspired by a parameter-free-type algorithms arising from convex (online) optimization literature. \nThe talk is based on joint works with C. Giraud\, Z. Li\, and G. Stoltz \n  \n  \nOrganizers: \nAnna KORBA (CREST)\, Karim LOUNICI (CMAP) \, Jaouad MOURTADA (CREST) \nSponsors:\nCREST-CMAP \n
URL:https://crest.science/event/evgenii-chzhen-cnrs-universite-paris-saclay-small-total-cost-constraints-in-contextual-bandits-with-knapsacks-with-some-applications-to-fairness/
CATEGORIES:Seminars,Statistics
ATTACH;FMTTYPE=:
END:VEVENT
END:VCALENDAR