Generalising realisability in statistical learning theory under epistemic uncertainty

2024/02/22 by Fabio Cuzzolin, Cuzzolin, Fabio
Mathematics · Computer Science · #Statistics Education and Methodologies #Machine Learning and Algorithms

paper · pdf · doi:10.48550/arxiv.2402.14759

Abstract

The purpose of this paper is to look into how central notions in statistical learning theory, such as realisability, generalise under the assumption that train and test distribution are issued from the same credal set, i.e., a convex set of probability distributions. This can be considered as a first step towards a more general treatment of statistical learning under epistemic uncertainty.

Related

• Credal Learning Theory
• A calibration test for evaluating set-based epistemic uncertainty representations
• Is the Volume of a Credal Set a Good Measure for Epistemic Uncertainty?
• Equivalences between learning of data and probability distributions, and their applications
• Quantifying Aleatoric and Epistemic Uncertainty with Proper Scoring Rules