84 citations
- Huyên Pham2 profiles4
- Olivier Wintenberger4 · h 19
- Benoît Laslier3 · h 11
- Clément Levrard2 profiles3 · h 11
- Étienne Roquain3 · h 20
- Idris Kharroubi2 profiles3 · h 17
- N. Frikha3 · h 13
- Romain Dujardin2 profiles3 · h 21
- A. Millet2 · h 26
- Antoine Godichon‐Baggioni2
- Bastien Chassagnol2
- Bruno Portier2 profiles2 · h 10
- Laboratoire de Probabilités et Modèles AléatoiresFR55 papers
- Université Paris CitéFR20 papers
- Sorbonne UniversitéFR15 papers
- Centre National de la Recherche ScientifiqueFR12 papers
- École PolytechniqueFR8 papers
- Laboratoire de Mathématiques Blaise PascalFR8 papers
- Centre de Mathématiques Appliquées de l'École polytechniqueFR7 papers
- Laboratoire de Physique Théorique et Modèles StatistiquesFR7 papers
- Sorbonne Paris CitéFR7 papers
- Département mathématiques, informatique, sciences de la donnée et technologies du numériqueFR4 papers
- Laboratoire de Mathématiques d'OrsayFR4 papers
- Laboratoire de Mathématiques et Modélisation d'ÉvryFR4 papers
5 papers · 1 filter
Monte Carlo guided Diffusion for Bayesian linear inverse problems
Gabriel Cardoso, Yazid Janati El Idrissi, Sylvain Le Corff +1
Ill-posed linear inverse problems arise frequently in various applications, from computational photography to medical imaging. A recent line of research exploits Bayesian inference…
Actor-Critic learning for mean-field control in continuous time
Noufel Frikha, Maximilien Germain, Mathieu Laurière +2
We study policy gradient for mean-field control in continuous time in a reinforcement learning setting. By considering randomised policies with entropy regularisation, we derive a…
Sparse tree-based initialization for neural networks
Patrick Lutz, Ludovic Arnould, Claire Boyer +1
Dedicated neural network (NN) architectures have been designed to handle specific data types (such as CNN for images or RNN for text), which ranks them among state-of-the-art metho…
Framing RNN as a kernel method: A neural ODE approach
Adeline Fermanian, Pierre Marion, Jean-Philippe Vert +1
Building on the interpretation of a recurrent neural network (RNN) as a continuous-time neural differential equation, we show, under appropriate conditions, that the solution of a…
High-dimensional robust regression and outliers detection with SLOPE
Alain Virouleau, Agathe Guilloux, Stéphane Gaïffas +1
The problems of outliers detection and robust regression in a high-dimensional setting are fundamental in statistics, and have numerous applications. Following a recent set of work…