Recherche - Archive ouverte HAL Accéder directement au contenu

Filtrer vos résultats

11 résultats

Pay attention to your loss: understanding misconceptions about 1-Lipschitz neural networks

Louis Béthune , Thibaut Boissin , Mathieu Serrurier , Franck Mamalet , Corentin Friedrich , et al.
Advances in Neural Information Processing Systems, Nov 2022, New Orleans, United States. ⟨10.48550/arXiv.2104.05097⟩
Communication dans un congrès hal-03872080v1
Image document

Transport-based Counterfactual Models

Lucas de Lara , Alberto González-Sanz , Nicholas Asher , Laurent Risser , Jean-Michel Loubes
2023
Pré-publication, Document de travail hal-03216124v3
Image document

Central Limit Theorems for General Transportation Costs

Eustasio del Barrio , Alberto González-Sanz , Jean-Michel Loubes
2021
Pré-publication, Document de travail hal-03136113v2

Achieving robustness in classification using optimal transport with hinge regularization

Mathieu Serrurier , Franck Mamalet , Alberto González-Sanz , Thibaut Boissin , Jean-Michel Loubes , et al.
Conference on Computer Vision and Pattern Recognition, Jun 2021, Virtuel, Canada. ⟨10.1109/CVPR46437.2021.00057⟩
Communication dans un congrès hal-03033400v1
Image document

Two-sample goodness-of-fit tests on the flat torus based on Wasserstein distance and their relevance to structural biology

Javier González-Delgado , Alberto González-Sanz , Juan Cortés , Pierre Neuvial
Electronic Journal of Statistics , 2023, 17 (1), pp.1547-1586. ⟨10.1214/23-EJS2135⟩
Article dans une revue hal-03369795v3
Image document

GAN Estimation of Lipschitz Optimal Transport Maps

Alberto González-Sanz , Lucas de Lara , Louis Béthune , Jean-Michel Loubes
2022
Pré-publication, Document de travail hal-03575178v1
Image document

A Consistent Extension of Discrete Optimal Transport Maps for Machine Learning Applications

Lucas de Lara , Alberto González-Sanz , Jean-Michel Loubes
2021
Pré-publication, Document de travail hal-03142788v1
Image document

Diffeomorphic Registration using Sinkhorn Divergences

Lucas de Lara , Alberto González-Sanz , Jean-Michel Loubes
2022
Pré-publication, Document de travail hal-03705992v2
Image document

A Central Limit Theorems for Semidiscrete Wasserstein Distances

Eustasio del Barrio , Alberto González-Sanz , Jean-Michel Loubes
2023
Pré-publication, Document de travail hal-03232450v3

Tackling Algorithmic Bias in Neural-Network Classifiers using Wasserstein-2 Regularization

Laurent Risser , Alberto González-Sanz , Quentin Vincenot , Jean-Michel Loubes
Journal of Mathematical Imaging and Vision, 2022
Article dans une revue hal-03324550v1

Gaussian Processes on Distributions based on Regularized Optimal Transport

François Bachoc , Louis Béthune , Alberto González-Sanz , Jean-Michel Loubes
26th International Conference on Artificial Intelligence and Statistics (AISTATS 2023), Apr 2023, Valencia, Spain. ⟨10.48550/arXiv.2210.06574⟩
Communication dans un congrès hal-03981114v1