I Bet You Did Not Mean That: Testing Semantic Importance via Betting
I Bet You Did Not Mean That: Testing Semantic Importance via Betting
Recent works have extended notions of feature importance to \emph{semantic concepts} that are inherently interpretable to the users interacting with a black-box predictive model. Yet, precise statistical guarantees, such as false positive rate control, are needed to communicate findings transparently and to avoid unintended consequences in real-world scenarios. In this …