BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//wp-events-plugin.com//7.2.3.1//EN
BEGIN:VEVENT
UID:894@lincs.fr
DTSTART;TZID=Europe/Paris:20250411T110000
DTEND;TZID=Europe/Paris:20250411T120000
DTSTAMP:20250407T111644Z
URL:https://www.lincs.fr/events/optimally-deceiving-a-learning-in-stackelb
 erg-games/
SUMMARY:Optimally deceiving a learning leader in Stackelberg games
DESCRIPTION:Andrea Araldo will present the setting and some interesting
 proofs contained in the NeurIPS 2020 paper "Optimally deceiving a learning
 leader in Stackelberg games".\n\nTo ground the discussion in a concrete
 context\, I will discuss the paper is a demand-side management
 scenario.\n\nThe regulator (e.g.\, the government - acting as a leader)
 proposes incentives to  users (followers)\, to convince them to switch to
 sustainable alternatives (e.g.\, when choosing products or services). The
 regulator optimizes such incentives with the goal of maximizing social
 welfare. Users choose alternatives so as to maximize their utility
 function. The regulator has only partial information about the users' true
 utility function. Therefore\, users can can manipulate the regulator\, by
 choosing alternatives according to a "fake" utility function\, different
 than their true one. By doing so\, users can mislead the regulator and
 receive more favourable incentives than they would deserve. The paper
 shows analytically under which conditions users can basically mislead the
 regulator as much as they want.\n
CATEGORIES:Network Theory,Working Group
LOCATION:Zoom + Amphi 5 chez Télécom-Paris\, 19 place Marguerite Perey\,
 Palaiseau\, 91120\, France
X-APPLE-STRUCTURED-LOCATION;VALUE=URI;X-ADDRESS=19 place Marguerite Perey\,
 Palaiseau\, 91120\, France;X-APPLE-RADIUS=100;X-TITLE=Zoom + Amphi 5 chez
 Télécom-Paris:geo:0,0
END:VEVENT
BEGIN:VTIMEZONE
TZID:Europe/Paris
X-LIC-LOCATION:Europe/Paris
BEGIN:DAYLIGHT
DTSTART:20250330T030000
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
END:DAYLIGHT
END:VTIMEZONE
END:VCALENDAR