A User's Guide to Sampling Strategies for Sliced Optimal Transport
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866918056097218560 |
|---|---|
| author | Sisouk, Keanu Delon, Julie Tierny, Julien |
| author_facet | Sisouk, Keanu Delon, Julie Tierny, Julien |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_02275 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A User's Guide to Sampling Strategies for Sliced Optimal Transport Sisouk, Keanu Delon, Julie Tierny, Julien Machine Learning Probability 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. |
| title | A User's Guide to Sampling Strategies for Sliced Optimal Transport |
| topic | Machine Learning Probability |
| url | https://arxiv.org/abs/2502.02275 |