Enregistré dans:
Détails bibliographiques
Auteurs principaux: Caprio, Michele, Sultana, Maryam, Elia, Eleni, Cuzzolin, Fabio
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:https://arxiv.org/abs/2402.00957
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866909362369331200
author Caprio, Michele
Sultana, Maryam
Elia, Eleni
Cuzzolin, Fabio
author_facet Caprio, Michele
Sultana, Maryam
Elia, Eleni
Cuzzolin, Fabio
contents Statistical learning theory is the foundation of machine learning, providing theoretical bounds for the risk of models learned from a (single) training set, assumed to issue from an unknown probability distribution. In actual deployment, however, the data distribution may (and often does) vary, causing domain adaptation/generalization issues. In this paper we lay the foundations for a `credal' theory of learning, using convex sets of probabilities (credal sets) to model the variability in the data-generating distribution. Such credal sets, we argue, may be inferred from a finite sample of training sets. Bounds are derived for the case of finite hypotheses spaces (both assuming realizability or not), as well as infinite model spaces, which directly generalize classical results.
format Preprint
id arxiv_https___arxiv_org_abs_2402_00957
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Credal Learning Theory
Caprio, Michele
Sultana, Maryam
Elia, Eleni
Cuzzolin, Fabio
Machine Learning
Artificial Intelligence
Statistical learning theory is the foundation of machine learning, providing theoretical bounds for the risk of models learned from a (single) training set, assumed to issue from an unknown probability distribution. In actual deployment, however, the data distribution may (and often does) vary, causing domain adaptation/generalization issues. In this paper we lay the foundations for a `credal' theory of learning, using convex sets of probabilities (credal sets) to model the variability in the data-generating distribution. Such credal sets, we argue, may be inferred from a finite sample of training sets. Bounds are derived for the case of finite hypotheses spaces (both assuming realizability or not), as well as infinite model spaces, which directly generalize classical results.
title Credal Learning Theory
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2402.00957