Accumulated Aggregated D-Optimal Designs for Estimating Main Effects in Black-Box Models

ArXi:2510.08465v2 Announce Type: replace-cross Estimating how individual input variables affect the output of a black-box model is a central task in explainable machine learning. However, existing methods suffer from two key limitations: sensitivity to out-of-distribution (OOD) evaluations, which arises when query points are placed far from the data manifold, and instability under feature correlation, which can lead to unreliable effect estimates in practice. We