Equivalence of the Empirical Risk Minimization to Regularization on the Family of f-Divergences - HAL Accéder directement au contenu
Communication dans un congrès Année : 2024

Equivalence of the Empirical Risk Minimization to Regularization on the Family of f-Divergences

Résumé

The solution to empirical risk minimization with f-divergence regularization (ERM-fDR) is presented under mild conditions on f. Under such conditions, the optimal measure is shown to be unique. Examples of the solution for particular choices of the function f are presented. Previously known solutions to common regularization choices are obtained by leveraging the flexibility of the family of f-divergences. These include the unique solutions to empirical risk minimization with relative entropy regularization (Type-I and Type-II). The analysis of the solution unveils the following properties of f-divergences when used in the ERM-fDR problem: i) f-divergence regularization forces the support of the solution to coincide with the support of the reference measure, which introduces a strong inductive bias that dominates the evidence provided by the training data; and ii) any f-divergence regularization is equivalent to a different f-divergence regularization with an appropriate transformation of the empirical risk function.
Fichier principal
Vignette du fichier
ISIT_2024a_HAL_V2.pdf ( 529.17 Ko ) Télécharger
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-04431558, version 1 (01-02-2024)
hal-04431558, version 2 (16-05-2024)

Licence

Paternité - CC BY 4.0

Identifiants

  • HAL Id : hal-04431558 , version 2

Citer

Francisco Daunas, Iñaki Esnaola, Samir M Perlaza, H. Vincent Poor. Equivalence of the Empirical Risk Minimization to Regularization on the Family of f-Divergences. Proceedings of the IEEE International Symposium on Information Theory, IEEE, Jul 2024, Athens, Greece. ⟨hal-04431558v2⟩
86 Consultations
47 Téléchargements
Dernière date de mise à jour le 26/06/2024
comment ces indicateurs sont-ils produits

Partager

Gmail Facebook Twitter LinkedIn Plus