1.4k citations
- École Normale Supérieure Paris-SaclayFR117 papers
- Centre National de la Recherche ScientifiqueFR97 papers
- Université Paris-SaclayFR24 papers
- Commissariat à l'Énergie Atomique et aux Énergies AlternativesFR20 papers
- École PolytechniqueFR18 papers
- University of Hong KongHK12 papers
- Le LAMAFR11 papers
- CEA DAM Île-de-FranceFR10 papers
- University College DublinIE10 papers
- Centre de Recherche en Mathématiques de la DécisionFR9 papers
- Université Savoie Mont BlancFR9 papers
- CEA Paris-SaclayFR8 papers
165 papers
Maximum Entropy Semi-Supervised Inverse Reinforcement Learning
Julien Audiffren, Michal Valko, Alessandro Lazaric +1
A popular approach to apprenticeship learning (AL) is to formulate it as an inverse reinforcement learning (IRL) problem. The MaxEnt-IRL algorithm successfully integrates the maxim…
Persistence and bimodality of large-scale turbulent structures across a Rayleigh-Taylor layer: Impact on transport and physical modelling through two-field-conditional correlations
R. Watteaux, J. A. Redford, A. Llor
The distribution functions of field fluctuations of the turbulent mixing layer produced by a Rayleigh-Taylor instability (RTI) have long been hypothesized to involve bimodal effect…
Fast and Scalable Optimal Transport for Brain Tractograms
Jean Feydy, Pierre Roussillon, Alain Trouvé +1
We present a new multiscale algorithm for solving regularized Optimal Transport problems on the GPU, with a linear memory footprint. Relying on Sinkhorn divergences which are conve…
NEO: Non Equilibrium Sampling on the Orbit of a Deterministic Transform
Achille Thin, Yazid Janati, Sylvain Le Corff +5
Sampling from a complex distribution and approximating its intractable normalizing constant Z are challenging problems. In this paper, a novel family of importance samplers (IS…
Convergence Analysis of Riemannian Stochastic Approximation Schemes
Alain Durmus, Pablo Jiménez, Éric Moulines +2
This paper analyzes the convergence for a large class of Riemannian stochastic approximation (SA) schemes, which aim at tackling stochastic optimization problems. In particular, th…
Kernel Operations on the GPU, with Autodiff, without Memory Overflows
Benjamin Charlier, Jean Feydy, Joan Alexis Glaunès +2
The KeOps library provides a fast and memory-efficient GPU support for tensors whose entries are given by a mathematical formula, such as kernel and distance matrices. KeOps allevi…