From Shapley back to Pearson: Hypothesis Testing via the Shapley Value. (arXiv:2207.07038v3 [cs.LG] UPDATED)

The complex nature of artificial neural networks raises concerns on their
reliability, trustworthiness, and fairness in real-world scenarios. The Shapley
value -- a solution concept from game theory -- is one of the most popular
explanation methods for machine learning models. More traditionally, from the
perspective of statistical learning, feature importance is defined in terms of
conditional independence. So far, these two approaches to interpretability and
feature importance have been considered separate and distinct. In this work, we
show that …

arxiv hypothesis pearson testing value