3.6k citations
- Université Paris-SaclayFR516 papers
- Centre National de la Recherche ScientifiqueFR456 papers
- Laboratoire des signaux et systèmesFR172 papers
- Université Paris-SudFR86 papers
- SupélecFR79 papers
- Institut national de recherche en sciences et technologies du numériqueFR72 papers
- Mathématiques et Informatique pour la Complexité et les Systèmes57 papers
- Commissariat à l'Énergie Atomique et aux Énergies AlternativesFR52 papers
- Université de LorraineFR43 papers
- École Centrale ParisFR37 papers
- Sorbonne UniversitéFR37 papers
- CEA Paris-SaclayFR28 papers
5 papers · 2 filters
On the Calibration of Epistemic Uncertainty: Principles, Paradoxes and Conflictual Loss
Mohammed Fellaji, Frédéric Pennerath, Brieuc Conan-Guez +1
The calibration of predictive distributions has been widely studied in deep learning, but the same cannot be said about the more specific epistemic uncertainty as produced by Deep…
Gaussian process interpolation with conformal prediction: methods and comparative analysis
Aurélien Pion, Emmanuel Vazquez
This article advocates the use of conformal prediction (CP) methods for Gaussian process (GP) interpolation to enhance the calibration of prediction intervals. We begin by illustra…
Gegenbauer Graph Neural Networks for Time-varying Signal Reconstruction
Jhon A. Castro-Correa, Jhony H. Giraldo, Mohsen Badiey +1
Reconstructing time-varying graph signals (or graph time-series imputation) is a critical problem in machine learning and signal processing with broad applications, ranging from mi…
Multiple-Input Fourier Neural Operator (MIFNO) for source-dependent 3D elastodynamics
Fanny Lehmann, Filippo Gatti, Didier Clouteau
Numerical simulations are essential tools to evaluate the solution of the wave equation in complex settings, such as three-dimensional (3D) domains with heterogeneous properties. H…
Retrieval Augmented Deep Anomaly Detection for Tabular Data
Hugo Thimonier, Fabrice Popineau, Arpad Rimmel +1
Deep learning for tabular data has garnered increasing attention in recent years, yet employing deep models for structured data remains challenging. While these models excel with u…