Machine Unlearning for Gibbs Supervised Learning Algorithms
A variational formulation inspired by empirical risk minimization subject to relative entropy regularization (ERM-RER) is proposed using a variational formulation inspired by empirical risk minimization subject to relative entropy regularization to guarantee exact unlearning for Gibbs supervised learning algorithms.
Yaiza Bermudez, S. Perlaza, Iñaki Esnaola
· International Symposium on I... · 2 citations