Portrait de Vincent Quirion

Vincent Quirion

Maîtrise recherche - UdeM
Superviseur⋅e principal⋅e
Ioannis Mitliagkas
Sujets de recherche
Apprentissage par renforcement
Désapprentissage
Réseaux de neurones en graphes

Publications

Unlearning with Asymmetric Sources: Improved Unlearning-Utility Trade-off with Public Data
Ahmed Mehdi Inane
Vincent Quirion
Gintare Karolina Dzugaite
Ioannis Mitliagkas
Noise-based certified machine unlearning currently faces a hard ceiling: the noise magnitude required to certify unlearning typically destro… (voir plus)ys model utility, particularly for large-scale deletion requests. While leveraging public data is a standard technique in differential privacy to relax this tension, its role in unlearning remains unexplored. We address this gap by introducing Asymmetric Langevin Unlearning (ALU), a framework that uses public data to mitigate privacy costs. We prove that public data injection suppresses the unlearning cost by a factor of
2026-05-10
arXiv (prépublication)
doi.org
arxiv.org