81 citations
Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.
- Centre National de la Recherche ScientifiqueFR13 papers
- Université Paris-SaclayFR9 papers
- Commissariat à l'Énergie Atomique et aux Énergies AlternativesFR7 papers
- CEA Paris-SaclayFR5 papers
- Université Paris-SudFR5 papers
- Centre de Recherche en Informatique, Signal et Automatique de LilleFR3 papers
- Université de LilleFR3 papers
- Biochimie des Protéines MembranairesFR2 papers
- École Centrale de LilleFR2 papers
- Eindhoven University of TechnologyNL2 papers
- InsermFR2 papers
- Institut CurieFR2 papers
4 papers · 1 filter
Optimal Stopping in Latent Diffusion Models
Yu-Han Wu, Quentin Berthet, Gérard Biau +3
We identify and analyze a surprising phenomenon of Latent Diffusion Models (LDMs) where the final steps of the diffusion can degrade sample quality. In contrast to conventional arg…
When Pattern-by-Pattern Works: Theoretical and Empirical Insights for Logistic Models with Missing Values
Christophe Muller, Erwan Scornet, Julie Josse
Predicting with missing inputs challenges even parametric models, as parameter estimation alone is insufficient for prediction on incomplete data. While several works study predict…
Dealing with Unknown Variances in Best-Arm Identification
Marc Jourdan, Rémy Degenne, Emilie Kaufmann
The problem of identifying the best arm among a collection of items having Gaussian rewards distribution is well understood when the variances are known. Despite its practical rele…
Risk-aware linear bandits with convex loss
Patrick Saux, Odalric-Ambrym Maillard
In decision-making problems such as the multi-armed bandit, an agent learns sequentially by optimizing a certain feedback. While the mean reward criterion has been extensively stud…