Trust Regions for Explanations via Black-Box Probabilistic Certification

arXiv:2402.11168v1 Announce Type: new
Abstract: Given the black box nature of machine learning models, a plethora of explainability methods have been developed to decipher the factors behind individual decisions. In this paper, we introduce a novel problem of black box (probabilistic) explanation certification. We ask the question: Given a black box model with only query access, an explanation for an example and a quality metric (viz. fidelity, stability), can we find the largest hypercube (i.e., $\ell_{\infty}$ ball) centered at the …

abstract arxiv black box box certification cs.ai cs.lg decisions explainability machine machine learning machine learning models nature novel paper question trust type via