CIMPA-ICTP Fellowships "Research in Pairs"
Probabilistic values on cooperative game theory and their applications in machine learning
10 – 13 June, 2025
Participant
Bertrand Mbama Engoulou (University of Douala)
Participate in the CIMPA-ICTP online course
The course will be given in English on zoom.
This is a recurrent meeting, so please register only once for all 4 sessions:
https://us02web.zoom.us/meeting/register/pauzSGrrS7qcygjJW42htQ#/registration
The course will take place on the following days (Paris time zone):
- Tuesday 10 June: 2pm – 4pm
- Wednesday 11 June: 2pm – 4pm
- Thursday 12 June: 2pm – 4pm
- Friday 13 June: 2pm – 4pm
Abstract: Game theory is a mathematical theory which deals with situations in which two or more individuals (players) interact and thereby jointly determine the outcome. Game theory has two principal branches; cooperative games and noncooperative games. In this course, we are only interested by cooperative games. We present concepts of : cooperative games (with transferable utility), core of a cooperative game, and probabilistic values. Note that, on cooperative games, values are used to evaluate each player’s contribution to the collective outcome. The most famous of them is the Shapley value. The measure of individual’s contributions is also a major preoccupation in machine learning. In fact, with the proliferation of black-box models, people are concerned about the influence of each feature on the prediction made by a model of machine learning. In the application part of this course, we use the Shapley value to evaluate each feature’s influence. For that, from the model of machine learning, we construct a cooperative game in which features correspond to players.
Domain : Game theory # probability# statistics
MSC : 60A05 # 62J02 # 68T05 # 91A12
Keywords : Cooperative games # Shapley value # Machine learning # Interpretability # Predictive
modeling
SPONSORS
