Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methods

TL;DR

This paper introduces the concepts of aleatoric and epistemic uncertainty in machine learning, emphasizing their importance for safety and reliability, and reviews existing methods for handling and formalizing these uncertainties.

Contribution

It provides an overview of uncertainty types in machine learning and surveys current approaches to distinguish and manage aleatoric and epistemic uncertainty.

Findings

Highlights the importance of uncertainty quantification for safety-critical applications.

Reviews methods for modeling and separating aleatoric and epistemic uncertainty.

Discusses challenges and future directions in uncertainty estimation.

Abstract

The notion of uncertainty is of major importance in machine learning and constitutes a key element of machine learning methodology. In line with the statistical tradition, uncertainty has long been perceived as almost synonymous with standard probability and probabilistic predictions. Yet, due to the steadily increasing relevance of machine learning for practical applications and related issues such as safety requirements, new problems and challenges have recently been identified by machine learning scholars, and these problems may call for new methodological developments. In particular, this includes the importance of distinguishing between (at least) two different types of uncertainty, often referred to as aleatoric and epistemic. In this paper, we provide an introduction to the topic of uncertainty in machine learning as well as an overview of attempts so far at handling uncertainty in general and formalizing this distinction in particular.