Ms. Yaiza Bermudez - Communication systems
Date: - Location: Eurecom
Abstract: 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. Short bio: Yaiza Bermudez is a Ph.D. student at Centre Inria d’Université Côte d’Azur, France, under the supervision of Samir M. Perlaza and Iñaki Esnaola. She received the M.Sc. degree in Computer Science from ENSIMAG, Grenoble-INP, France, with high honors in 2024, and the B.Sc. degree in Mathematics and Computer Science from Aix-Marseille University (AMU), France, with honors in 2022. Recognition of her work includes the 2026 Jack Keil Wolf ISIT Student Paper Award for the paper “Machine Unlearning for Gibbs Supervised Learning Algorithms.”
