Enregistré dans:
Détails bibliographiques
Auteurs principaux: Ardeshir, Navid, Deng, Samuel, Hsu, Daniel, Liu, Jingwen
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:https://arxiv.org/abs/2601.16922
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866915750885720064
author Ardeshir, Navid
Deng, Samuel
Hsu, Daniel
Liu, Jingwen
author_facet Ardeshir, Navid
Deng, Samuel
Hsu, Daniel
Liu, Jingwen
contents The sample complexity of multi-group learning is shown to improve in the group-realizable setting over the agnostic setting, even when the family of groups is infinite so long as it has finite VC dimension. The improved sample complexity is obtained by empirical risk minimization over the class of group-realizable concepts, which itself could have infinite VC dimension. Implementing this approach is also shown to be computationally intractable, and an alternative approach is suggested based on improper learning.
format Preprint
id arxiv_https___arxiv_org_abs_2601_16922
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Group-realizable multi-group learning by minimizing empirical risk
Ardeshir, Navid
Deng, Samuel
Hsu, Daniel
Liu, Jingwen
Machine Learning
The sample complexity of multi-group learning is shown to improve in the group-realizable setting over the agnostic setting, even when the family of groups is infinite so long as it has finite VC dimension. The improved sample complexity is obtained by empirical risk minimization over the class of group-realizable concepts, which itself could have infinite VC dimension. Implementing this approach is also shown to be computationally intractable, and an alternative approach is suggested based on improper learning.
title Group-realizable multi-group learning by minimizing empirical risk
topic Machine Learning
url https://arxiv.org/abs/2601.16922