Publications
| [1] | Vincent Plassier, Maxime Vono, Alain Durmus, Eric Moulines: DG-LMC: A Turn-key and Scalable Synchronous Distributed MCMC Algorithm via Langevin Monte Carlo within Gibbs. International Conference on Machine Learning (ICML) (2021). [ ArXiv ] |
| [2] | Vincent Plassier, Maxime Vono, Alain Durmus, Aymeric Dieuleveut, Eric Moulines: QLSD: Quantised Langevin Stochastic Dynamics for Bayesian Federated Learning. International Conference on Artificial Intelligence and Statistics (AISTATS) (2022). [ Proceedings ] |
| [3] | Hamid Jalalzai*, Elie Kadoche*, Rémi Leluc* and Vincent Plassier*: Membership Inference Attacks via Adversarial Examples. NeurIPS Workshop on Trustworthy and Socially Responsible Machine Learning (2022). [ ArXiv ] |
| [4] | Vincent Plassier, Alain Durmus, Eric Moulines: Federated averaging Langevin Dynamics: Toward a unified theory and new algorithms. International Conference on Artificial Intelligence and Statistics (AISTATS) (2022). [ Proceedings ] |
| [5] | Vincent Plassier, François Portier and Johan Segers: Risk bounds when learning infinitely many response functions by ordinary linear regression. Annales de l'Institut Henri Poincaré (AIHP) (2023). [ ArXiv ] |
| [6] | Vincent Plassier, Mehdi Makni, Aleksandr Rubashevskii, Eric Moulines and Maxim Panov: Conformal Prediction for Federated Uncertainty Quantification Under Label Shift. In International Conference on Machine Learning (2023). [ ArXiv ] |
| [7] | Vincent Plassier, Nikita Kotelevskii, Aleksandr Rubashevskii, Fedor Noskov, Maksim Velikanov, Alexander Fishkov, Samuel Horvath, Martin Takac, Eric Moulines and Maxim Panov: Efficient Conformal Prediction under Data Heterogeneity. International Conference on Artificial Intelligence and Statistics (AISTATS) (2024). [ ArXiv ] |
| [8] | Vincent Plassier, Alexander Fishkov, Eric Moulines and Maxim Panov: Conditionally valid Probabilistic Conformal Prediction. Preprint . [ ArXiv ] |
| [9] | Vincent Plassier, Alexander Fishkov, Eric Moulines and Maxim Panov: Generalized Conformalized Quantile Regression: A New Approach for Better Conditional Coverage. Preprint . |