BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//AMSE//Event Calendar//FR
CALSCALE:GREGORIAN
METHOD:PUBLISH
BEGIN:VEVENT
UID:event-13189@amse-aixmarseille.fr
DTSTAMP:20260920T125801Z
CREATED:20260920T125801Z
LAST-MODIFIED:20260920T125801Z
STATUS:CONFIRMED
SEQUENCE:0
SUMMARY:Big data and econometrics seminar - Paul-Gauthier Noé
DTSTART:20260915T120000Z
DTEND:20260915T131500Z
DESCRIPTION:Shapley values are extensively used to measure the contribution
  of the inputs to a function’s output. However\, originating in cooperati
 ve game theory\, they are defined for real-valued functions only\, limiting
  their application.In statistics and machine learning\, models can output e
 lements in a multidimensional vector space. As an example\, in a classifica
 tion task\, the output space can be the multidimensional probability simple
 x. In this case\, Shapley compositions\, which are basically Shapley vector
 s in the Euclidean Aitchison simplex\, can be defined. In this seminar\, I 
 will present this use case and discuss ongoing work on generalising Shapley
 's framework to vector-valued functions.\\n\\nContact: Sullivan Hué - sull
 ivan.hue[at]univ-amu.frMichel Lubrano - michel.lubrano[at]univ-amu.fr\n\nPl
 us d'informations: https://amse-aixmarseille.fr/en/events/paul-gauthier-noe
LOCATION:Îlot Bernard du Bois - Salle 16\, AMU - AMSE\, 5-9 boulevard Maur
 ice Bourdet\, 13001 Marseille
URL;VALUE=URI:https://amse-aixmarseille.fr/en/events/paul-gauthier-noe
CONTACT:Sullivan Hué - sullivan.hue[at]univ-amu.frMichel Lubrano - michel.
 lubrano[at]univ-amu.fr
TRANSP:OPAQUE
END:VEVENT
END:VCALENDAR