200 citations
- Centre National de la Recherche ScientifiqueFR29 papers
- École Nationale Supérieure d'Ingénieurs de CaenFR25 papers
- Université de Caen NormandieFR20 papers
- Normandie UniversitéFR12 papers
- Centre de Recherche en Mathématiques de la DécisionFR8 papers
- CEA Paris-SaclayFR5 papers
- Commissariat à l'Énergie Atomique et aux Énergies AlternativesFR5 papers
- Institut de Mathématiques de BordeauxFR5 papers
- Direction des EnergiesFR4 papers
- Université de SherbrookeCA4 papers
- DSM (Netherlands)NL3 papers
- Université Paris CitéFR3 papers
8 papers · 1 filter
Limits of non-local approximations to the Eikonal equation on manifolds
Jalal M. Fadili, Nicolas Forcadel, Rita Zantout
In this paper, we consider a non-local approximation of the time-dependent Eikonal equation defined on a Riemannian manifold. We show that the local and the non-local problems are…
An exploration of the balance game
Paul Dorbec, Michael A. Henning, Zsolt Tuza +1
The balance game is played on a graph by two players, Admirable (A) and Impish (I), who take turns selecting unlabeled vertices of . Admirable labels the selected vertices b…
Low Complexity Regularized Phase Retrieval
Jean-Jacques Godeme, Jalal Fadili
In this paper, we study the phase retrieval problem in the situation where the vector to be recovered has an a priori structure that can encoded into a regularization term. This re…
Evaluating Lexicon Incorporation for Depression Symptom Estimation
Kirill Milintsevich, Gaël Dias, Kairit Sirts
This paper explores the impact of incorporating sentiment, emotion, and domain-specific lexicons into a transformer-based model for depression symptom estimation. Lexicon informati…
The stochastic Ravine accelerated gradient method with general extrapolation coefficients
Hedy Attouch, Jalal Fadili, Vyacheslav Kungurtsev
In a real Hilbert space domain setting, we study the convergence properties of the stochastic Ravine accelerated gradient method for convex differentiable optimization. We consider…
Recovery Guarantees of Unsupervised Neural Networks for Inverse Problems trained with Gradient Descent
Nathan Buskulic, Jalal Fadili, Yvain Quéau
Advanced machine learning methods, and more prominently neural networks, have become standard to solve inverse problems over the last years. However, the theoretical recovery guara…