From the 5 of 52 papers with an AI index.
50 citations
- Centre National de la Recherche ScientifiqueFR30 papers
- Sorbonne UniversitéFR27 papers
- Université Paris Sciences et LettresFR21 papers
- Université Paris CitéFR19 papers
- Laboratoire de Physique de l'Ecole Normale SupérieureFR11 papers
- Département d'InformatiqueFR8 papers
- Laboratoire Kastler BrosselFR8 papers
- Sorbonne Paris CitéFR8 papers
- Département de mathématiques et applicationsFR6 papers
- Laboratoire MédiationsFR6 papers
- Université Paris-SaclayFR6 papers
- Collège de FranceFR5 papers
4 papers · 1 filter
Convergence Rates for Distribution Matching with Sliced Optimal Transport
Gauthier Thurin, Claire Boyer, Kimia Nadjahi
The paper analyzes an iterative sliced optimal transport method for matching probability distributions, providing non‑asymptotic convergence rates and showing how the method behave…
Generalization Bounds of Surrogate Policies for Combinatorial Optimization Problems
Pierre-Cyril Aubin-Frankowski, Yohann De Castro, Axel Parmentier +1
Many real-world decision problems require solving, again and again, combinatorial optimization instances drawn from a common distribution. A recent line of structured learning meth…
Adaptive multi-fidelity optimization with fast learning rates
Come Fiegel, Victor Gabillon, Michal Valko
In multi-fidelity optimization, biased approximations of varying costs of the target function are available. This paper studies the problem of optimizing a locally smooth function…
Gradient flow dynamics of shallow ReLU networks for square loss and orthogonal inputs
Etienne Boursier, Loucas Pillaud-Vivien, Nicolas Flammarion
The training of neural networks by gradient descent methods is a cornerstone of the deep learning revolution. Yet, despite some recent progress, a complete theory explaining its su…