Pitfalls of Epistemic Uncertainty Quantification through Loss Minimisation

Understand

Uncertainty quantification has received increasing attention in machine learning in the recent past.

• In particular, a distinction between aleatoric and epistemic uncertainty has been found useful in this regard.
• The latter refers to the learner's (lack of) knowledge and appears to be especially difficult to measure and quantify.
• In this paper, we analyse a recent proposal based on the idea of a second-order learner, which yields predictions in the form of distributions over probability distributions.