Article Dans Une Revue Transactions on Machine Learning Research Journal Année : 2025

A User's Guide to Sampling Strategies for Sliced Optimal Transport

Résumé

This paper serves as a user's guide to sampling strategies for sliced optimal transport. We provide reminders and additional regularity results on the Sliced Wasserstein distance. We detail the construction methods, generation time complexity, theoretical guarantees, and conditions for each strategy. Additionally, we provide insights into their suitability for sliced optimal transport in theory. Extensive experiments on both simulated and real-world data offer a representative comparison of the strategies, culminating in practical recommendations for their best usage.

Fichier principal
Vignette du fichier
main.pdf (11.18 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence

Dates et versions

hal-04932591 , version 1 (06-02-2025)
hal-04932591 , version 2 (14-04-2025)
hal-04932591 , version 3 (12-06-2025)

Licence

Identifiants

  • HAL Id : hal-04932591 , version 3

Citer

Keanu Sisouk, Julie Delon, Julien Tierny. A User's Guide to Sampling Strategies for Sliced Optimal Transport. Transactions on Machine Learning Research Journal, 2025. ⟨hal-04932591v3⟩
1445 Consultations
772 Téléchargements

Partager

  • More