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:20200329T010000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0300
TZOFFSETTO:+0200
TZNAME:EET
DTSTART:20201025T010000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=Europe/Helsinki:20200928T140000
DTEND;TZID=Europe/Helsinki:20200928T151500
DTSTAMP:20260712T130636
CREATED:20200917T130341Z
LAST-MODIFIED:20200917T130341Z
UID:12458-1601301600-1601306100@crest.science
SUMMARY:Tor LATTIMORE (DeepMind London) - " Improved Regret for Zeroth-Order Adversarial Bandit Convex Optimisation"
DESCRIPTION:\nThe Statistical Seminar: Every Monday at 2:00 pm.\nTime: 2:00 pm – 3:15 pm\nDate: 28th of september 2020\nPlace: Visio\nTor LATTIMORE (DeepMind London) – “Improved Regret for Zeroth-Order Adversarial Bandit Convex Optimisation“ \nAbstract: I will explain recent advances in adversarial bandit convex optimisation\, improving the best known minimax regret from O(d^(9.5) sqrt(n) log(n)^(7.5)) to O(d^(2.5) sqrt(n) log(n)) where d is the dimension and n is the number of interactions. The new analysis combines minimax duality with the information-theoretic Bayesian regret analysis by Russo and Van Roy as well as basic tools from asymptotic convex geometry. \nA preprint of this work is available at https://arxiv.org/pdf/2006.00475.pdf.\nOrganizers:\nCristina BUTUCEA (CREST)\, Alexandre TSYBAKOV (CREST)\, Karim LOUNICI (CMAP) \, Zoltan SZABO (CMAP)\nSponsors:\nCREST-CMAP\n \n\n
URL:https://crest.science/event/tor-lattimore-2/
CATEGORIES:Statistics
ATTACH;FMTTYPE=:
END:VEVENT
END:VCALENDAR