BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//AMSE//Event Calendar//FR
CALSCALE:GREGORIAN
METHOD:PUBLISH
BEGIN:VEVENT
UID:event-12554@www.amse-aixmarseille.fr
DTSTAMP:20260422T125848Z
CREATED:20260422T125848Z
LAST-MODIFIED:20260422T125848Z
STATUS:CONFIRMED
SEQUENCE:0
SUMMARY:big data and econometrics seminar - Marouane Il Idrissi
DTSTART:20251007T120000Z
DTEND:20251007T133000Z
DESCRIPTION:Cooperative game theory has become a cornerstone of post-hoc i
 nterpretability in machine learning\, largely through the use of Shapley va
 lues. Yet\, despite their widespread adoption\, Shapley-based methods often
  rest on axiomatic justifications whose relevance to feature attribution re
 mains debatable. During this presentation\, we will revisit cooperative gam
 e theory from an interpretability perspective and argue for a more principl
 ed use of its tools. Through two broad families of allocations\, we will pr
 ovide an intuitive interpretation of the Shapley values\, offer a blueprint
  for defining more intricate interpretation tools\, and derive statisticall
 y sound estimates to solve the exponential computational burden. Finally\, 
 we will discuss the theoretical challenges surrounding the choice of value 
 function.\\n\\nContact: Sullivan Hué: sullivan.hue[at]univ-amu.frMichel Lu
 brano: michel.lubrano[at]univ-amu.fr\n\nPlus d'informations: https://www.am
 se-aixmarseille.fr/en/events/marouane-il-idrissi-0
LOCATION:Îlot Bernard du Bois - Salle 24\, AMU - AMSE\, 5-9 boulevard Maur
 ice Bourdet\, 13001 Marseille
URL;VALUE=URI:https://www.amse-aixmarseille.fr/en/events/marouane-il-idrissi-0
CONTACT:Sullivan Hué: sullivan.hue[at]univ-amu.frMichel Lubrano: michel.lu
 brano[at]univ-amu.fr
TRANSP:OPAQUE
END:VEVENT
END:VCALENDAR