1.4k citations
- Centre National de la Recherche ScientifiqueFR13 papers
- Institut national de recherche en sciences et technologies du numériqueFR10 papers
- Sorbonne UniversitéFR8 papers
- Laboratoire d'Informatique Gaspard-MongeFR7 papers
- Télécom ParisFR6 papers
- Centre de Robotique5 papers
- Institut de Recherche en Informatique et Systèmes AléatoiresFR5 papers
- Université Gustave EiffelFR5 papers
- Hôpital Saint-MichelFR4 papers
- Laboratoire d’Informatique et SystèmesFR4 papers
- Laboratoire Traitement et Communication de l’InformationFR4 papers
- Technicolor (France)FR4 papers
12 papers · 1 filter
Multiple-Frequencies Population-Based Training
Waël Doulazmi, Auguste Lehuger, Marin Toromanoff +3
Reinforcement Learning's high sensitivity to hyperparameters is a source of instability and inefficiency, creating significant challenges for practitioners. Hyperparameter Optimiza…
GEPS: Boosting Generalization in Parametric PDE Neural Solvers through Adaptive Conditioning
Armand Kassaï Koupaï, Jorge Mifsut Benet, Yuan Yin +2
Solving parametric partial differential equations (PDEs) presents significant challenges for data-driven methods due to the sensitivity of spatio-temporal dynamics to variations in…
Winner-takes-all learners are geometry-aware conditional density estimators
Victor Letzelter, David Perera, Cédric Rommel +4
Winner-takes-all training is a simple learning paradigm, which handles ambiguous tasks by predicting a set of plausible hypotheses. Recently, a connection was established between W…
Fast Inference with Kronecker-Sparse Matrices
Antoine Gonon, Léon Zheng, Pascal Carrivain +1
Kronecker-sparse (KS) matrices -- whose supports are Kronecker products of identity and all-ones blocks -- underpin the structure of Butterfly and Monarch matrices and offer the pr…
Mesoscale Traffic Forecasting for Real-Time Bottleneck and Shockwave Prediction
Raphael Chekroun, Han Wang, Jonathan Lee +4
Accurate real-time traffic state forecasting plays a pivotal role in traffic control research. In particular, the CIRCLES consortium project necessitates predictive techniques to m…
Sparsity in neural networks can improve their privacy
Antoine Gonon, Léon Zheng, Clément Lalanne +3
This article measures how sparsity can make neural networks more robust to membership inference attacks. The obtained empirical results show that sparsity improves the privacy of t…