Conférence
Notice
Lieu de réalisation
IEEE International Symposium on Information Theory (ISIT), Guangzhou, China, Jun., 2026.
Langue :
Anglais
Crédits
Yaiza Bermudez (Intervention)
Conditions d'utilisation
Droit commun de la propriété intellectuelle
DOI : 10.60527/qgp1-z811
Citer cette ressource :
Yaiza Bermudez. DALI. Machine Unlearning for Gibbs Supervised Learning Algorithms . [Vidéo]. Canal-U. https://doi.org/10.60527/qgp1-z811. (Consultée le 6 novembre 2026)
logo DALI
Decisions, Algorithms, Learning, and Information
S'abonner
Contacter

Machine Unlearning for Gibbs Supervised Learning Algorithms

Mise en ligne : 29 juillet 2026
  • document 1 document 2 document 3
  • niveau 1 niveau 2 niveau 3
Descriptif

In this talk, a method for achieving exact unlearning for Gibbs supervised learning algorithms is proposed using a variational formulation inspired by empirical risk minimization subject to relative entropy regularization (ERM-RER). Such a method consists of maximizing the expected empirical risk over the dataset to be unlearned subject to a regularization by relative entropy with respect to the original algorithm. The optimization variable is a probability measure on the models; and the solution is another Gibbs probability measure that represents a new Gibbs supervised learning algorithm. The method guarantees exact unlearning in the sense that the new Gibbs algorithm coincides in distribution with the algorithm that would have been obtained by retraining from scratch on the dataset to be retained. As a byproduct, a framework for reweighting data points in ERM-RER by strategically choosing both the reference measure and the regularization factor is obtained. In this framework, exact unlearning is the special case in which zero-weight is assigned to the contribution of the data points to be unlearned. More generally, depending on the choice of certain parameters, data points can be up-weighted or down-weighted in ERM-RER problems for particular purposes, e.g., controlling the generalization error of Gibbs algorithms. This paves the way for new constructive or adversarial views on classical reweighting data points in ERM-RER.

Intervention / Responsable scientifique
Thème
Disciplines :

Avec les mêmes intervenants et intervenantes

Sur le même thème