This repository contains the code for the paper: Ensemble-based Uncertainty Quantification: Bayesian versus Credal Inference, written by Mohammad Hossein Shaker and Eyke Hüllermeier.

We consider ensemble-based approaches to uncertainty quantification, i.e., to derive meaningful measures of aleatoric and epistemic uncertainty in a prediction. In this regard, we propose a distinction between three types of uncertainty-aware learning algorithms: probabilistic agents, Bayesian agents, and Levi agents. We address the question of how to quantify aleatoric and epistemic uncertainty in a formal way, both for Bayesian and Levi agents, and how to approximate such quantities empirically using ensemble techniques. Moreover, we analyze the effectiveness of corresponding measures in an empirical study on classification with a reject option.