BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//wp-events-plugin.com//7.2.3.1//EN
BEGIN:VEVENT
UID:469@lincs.fr
DTSTART;TZID=Europe/Paris:20190918T140000
DTEND;TZID=Europe/Paris:20190918T150000
DTSTAMP:20190923T112451Z
URL:https://www.lincs.fr/events/talk-by-lorenzo-maggi/
SUMMARY:Backtrack bandit algorithms for cloud computing
DESCRIPTION:\nUnimodal functions arise whenever the expected value f(x) of
 the metric to be optimized has a single peak as a function of the available
 control variable x.\n\n\n\nThe exact shape of f is often not known in
 advance\, hence it can only be learned via sampling.\n\n\n\nFor this
 purpose\, we exploit the formalism of multi-armed bandits to design a
 learning algorithm that i) converges in probability to the optimal arm
 maximizing f and ii) does not require to know the learning horizon in
 advance\, i.e.\, it is “anytime”. Moreover\, it adapts naturally to the
 scenario where iii) prior knowledge on the location of the peak is
 available\, even if the prior is inaccurate.\n\n\n\nWe also present an
 efficient heuristic that can use explicitly the prior belief on the
 location of the optimal arm. We demonstrate the applicability of our
 approaches to a basic resource allocation problem for cloud computing\,
 where the orchestrator aims at adapting the resources allocated to a client
 to its unknown and dynamic requests.\n
CATEGORIES:Seminars
LOCATION:Paris-Rennes Room (EIT Digital)\, 23 avenue d'Italie\, 75013
 Paris\, France
X-APPLE-STRUCTURED-LOCATION;VALUE=URI;X-ADDRESS=23 avenue d'Italie\, 75013
 Paris\, France;X-APPLE-RADIUS=100;X-TITLE=Paris-Rennes Room (EIT
 Digital):geo:0,0
END:VEVENT
BEGIN:VTIMEZONE
TZID:Europe/Paris
X-LIC-LOCATION:Europe/Paris
BEGIN:DAYLIGHT
DTSTART:20190331T030000
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
END:DAYLIGHT
END:VTIMEZONE
END:VCALENDAR