English

Generalising realisability in statistical learning theory under epistemic uncertainty

Machine Learning 2024-02-23 v1 Artificial Intelligence Statistics Theory Statistics Theory

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.

Keywords

Cite

@article{arxiv.2402.14759,
  title  = {Generalising realisability in statistical learning theory under epistemic uncertainty},
  author = {Fabio Cuzzolin},
  journal= {arXiv preprint arXiv:2402.14759},
  year   = {2024}
}

Comments

arXiv admin note: text overlap with arXiv:2401.09435

R2 v1 2026-06-28T14:57:28.547Z