BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//jEvents 2.0 for Joomla//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
BEGIN:VEVENT
UID:09a066cc7c1c439986fd3519a2f30325
CATEGORIES:Seminars
CREATED:20260213T151919
SUMMARY:Lunch Seminar: Giorgio Stefano Gnecco - IMT Lucca
DESCRIPTION;ENCODING=QUOTED-PRINTABLE:\n\nOn the Approximation of the Shapley Value via Machine Learning in Trans
 portation Network Cooperative Games\n\n\nAbstract:\nThe Shapley value, a we
 ll-established concept in cooperative game theory, serves as a metric for a
 ssessing the significance of each player in a transferable utility game. Re
 cently, it has found application in gauging the importance of individual no
 des or arcs within a network. However, in this context, the exact evaluatio
 n of the Shapley value is often computationally expensive, particularly in 
 the case of extensive networks. This study delves into the challenge of app
 roximating the Shapley value in a transferable utility game defined on a ne
 twork, wherein the characteristics of the network are parameterized by a va
 riable of interest (e.g., the traffic demand). We examine the smoothness of
  the Shapley value with respect to this parameter and leverage such smoothn
 ess to theoretically justify the adoption of machine-learning techniques fo
 r its approximate computation. Additionally, we present potential extension
 s for further research in this area.\n
DTSTAMP:20260409T015605Z
DTSTART:20260223T130000Z
DTEND:20260223T140000Z
SEQUENCE:0
TRANSP:OPAQUE
END:VEVENT
END:VCALENDAR