LOCO Feature Importance Inference without Data Splitting via Minipatch Ensembles

ArXi:2206.02088v3 Announce Type: replace-cross Feature importance inference is critical for the interpretability and reliability of machine learning models. There has been increasing interest in developing model-agnostic approaches to interpret any predictive model, often in the form of feature occlusion or leave-one-covariate-out (LOCO) inference. Existing methods typically make limiting distributional assumptions, modeling assumptions, and require data splitting.