5 papers
Machine Unlearning for Gibbs Supervised Learning Algorithms
Yaiza Bermudez, Samir M. Perlaza, Iñaki Esnaola
In this paper, a method for achieving exact unlearning for Gibbs supervised learning algorithms is proposed using a variational formulation inspired by empirical risk minimization…
Equivalence Between Nested Gibbs Measures and Log-Linear Combinations of Gibbs Measures
Yaiza Bermudez, Samir M. Perlaza, Iñaki Esnaola
In this paper, three operations on Gibbs probability measures are studied. The first operation, often referred to as renormalization, takes one Gibbs probability measure and genera…
Decentralized Machine Learning with Centralized Performance Guarantees via Gibbs Algorithms
Yaiza Bermudez, Samir M. Perlaza, Iñaki Esnaola
In this paper, it is shown, for the first time, that centralized performance is achievable in decentralized learning without sharing the local datasets. Specifically, when clients…
Equivalence of optimal transport problems to regularization on the family of f-divergences
Maxime Nicaise, Yaiza Bermudez, Samir M. Perlaza
This work establishes that an optimal transport~(OT) problem regularized by a given -divergence admits the same solution as another OT problem regularized by a different -div…
Proofs for Folklore Theorems on the Radon-Nikodym Derivative
Yaiza Bermudez, Gaetan Bisson, Iñaki Esnaola +1
In this technical report, rigorous statements and formal proofs are presented for both foundational and advanced folklore theorems on the Radon-Nikodym derivative. The cases of con…