Research by Danny Fryer, PhD and collaborators.
February 2021
The Shapley value has become popular in the Explainable AI (XAI) literature, thanks, to a large extent, to a solid theoretical foundation, including four ``favourable and fair" axioms for attribution in transferable utility games.
October 2020
Under a weak assumption that the joint distribution is pseudo-elliptical, we obtain the asymptotic normality of the Shapley values.
October 2020
In this work, we consider an alternative and novel formulation which leads to the first instance of what we call model-independent Shapley values.
No papers match your search. Try “Shapley” or clear the search.