120 citations
- Université Paris CitéFR132 papers
- Département mathématiques, informatique, sciences de la donnée et technologies du numériqueFR88 papers
- Centre National de la Recherche ScientifiqueFR68 papers
- Laboratoire d’Analyse et de Mathématiques AppliquéesFR24 papers
- Délégation Paris 5FR20 papers
- Université Paris NanterreFR18 papers
- Université Paris-Est CréteilFR13 papers
- Laboratoire de Probabilités et Modèles AléatoiresFR11 papers
- Sorbonne Paris CitéFR11 papers
- Sorbonne UniversitéFR11 papers
- Université Gustave EiffelFR9 papers
- Laboratoire Jacques-Louis LionsFR8 papers
6 papers · 1 filter
Deep Neural Networks as Iterated Function Systems and a Generalization Bound
Jonathan Vacher
Deep neural networks (DNNs) achieve remarkable performance on a wide range of tasks, yet their mathematical analysis remains fragmented: stability and generalization are typically…
Transforming Conditional Density Estimation Into a Single Nonparametric Regression Task
Alexander G. Reisach, Olivier Collier, Alex Luedtke +1
We propose a way of transforming the problem of conditional density estimation into a single nonparametric regression task via the introduction of auxiliary samples. This allows le…
Plug-and-Play Posterior Sampling under Mismatched Measurement and Prior Models
Marien Renaud, Jiaming Liu, Valentin de Bortoli +2
Posterior sampling has been shown to be a powerful Bayesian approach for solving imaging inverse problems. The recent plug-and-play unadjusted Langevin algorithm (PnP-ULA) has emer…
Properties of Discrete Sliced Wasserstein Losses
Eloi Tanguy, Rémi Flamary, Julie Delon
The Sliced Wasserstein (SW) distance has become a popular alternative to the Wasserstein distance for comparing probability measures. Widespread applications include image processi…
Risk Minimization from Adaptively Collected Data: Guarantees for Supervised and Policy Learning
Aurélien Bibaut, Antoine Chambaz, Maria Dimakopoulou +2
Empirical risk minimization (ERM) is the workhorse of machine learning, whether for classification and regression or for off-policy policy learning, but its model-agnostic guarante…
Solving Inverse Problems by Joint Posterior Maximization with a VAE Prior
Mario González, Andrés Almansa, Mauricio Delbracio +2
In this paper we address the problem of solving ill-posed inverse problems in imaging where the prior is a neural generative model. Specifically we consider the decoupled case wher…