231 citations
- Télécom ParisFR7 papers
- Centre National de la Recherche ScientifiqueFR5 papers
- École Normale Supérieure - PSLFR4 papers
- EURECOMFR4 papers
- Huawei Technologies (China)CN4 papers
- Laboratoire d'Informatique Gaspard-MongeFR4 papers
- CentraleSupélecFR3 papers
- Laboratoire des signaux et systèmesFR3 papers
- Laboratoire Traitement et Communication de l’InformationFR3 papers
- Nanyang Technological UniversitySG3 papers
- Université de RennesFR3 papers
- Université Gustave EiffelFR3 papers
Showing 2022 · stat.MLShow all
2 papers · 2 filters
stat.ML2022★ 18 cited
How Much is Enough? A Study on Diffusion Times in Score-based Generative Models
Giulio Franzese, Simone Rossi, Lixuan Yang +4
Score-based diffusion models are a class of generative models whose dynamics is described by stochastic differential equations that map noise into data. While recent works have sta…
stat.ML2022★ 4 cited
Rate-Distortion Theoretic Bounds on Generalization Error for Distributed Learning
Milad Sefidgaran, Romain Chor, Abdellatif Zaidi
In this paper, we use tools from rate-distortion theory to establish new upper bounds on the generalization error of statistical distributed learning algorithms. Specifically, ther…