Quantifying Aleatoric and Epistemic Uncertainty in Machine Learning: Are Conditional Entropy and Mutual Information Appropriate Measures?

MCML Authors

Lisa Wimmer

→ Group Bernd Bischl
 Statistical Learning and Data Science

Yusuf Sale

→ Group Eyke Hüllermeier
 Artificial Intelligence and Machine Learning

Paul Hofman

→ Group Eyke Hüllermeier
 Artificial Intelligence and Machine Learning

Bernd Bischl

Prof. Dr.

Director

Statistical Learning and Data Science

Eyke Hüllermeier

Prof. Dr.

Principal Investigator

Artificial Intelligence and Machine Learning

Abstract

The quantification of aleatoric and epistemic uncertainty in terms of conditional entropy and mutual information, respectively, has recently become quite common in machine learning. While the properties of these measures, which are rooted in information theory, seem appealing at first glance, we identify various incoherencies that call their appropriateness into question. In addition to the measures themselves, we critically discuss the idea of an additive decomposition of total uncertainty into its aleatoric and epistemic constituents. Experiments across different computer vision tasks support our theoretical findings and raise concerns about current practice in uncertainty quantification.

inproceedings

---

UAI 2023

39th Conference on Uncertainty in Artificial Intelligence. Pittsburgh, PA, USA, Jul 31-Aug 03, 2023.

---

Authors

L. Wimmer • Y. Sale • P. Hofman • B. Bischl • E. Hüllermeier

---

Links

URL

---

Research Areas

 A1 | Statistical Foundations & Explainability

 A3 | Computational Models