Sliced Wasserstein distance between probability measures on Hilbert spaces
Fuente:
arXiv
Guardado en:
| Autor principal: | |
|---|---|
| Formato: | Preprint |
| Publicado: |
2023
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866911308703596544 |
|---|---|
| author | Han, Ruiyu |
| author_facet | Han, Ruiyu |
| contents | The sliced Wasserstein distance as well as its variants have been widely considered in comparing probability measures defined on $\mathbb R^d$. Here we derive the notion of sliced Wasserstein distance for measures on an infinite dimensional separable Hilbert spaces, depict the relation between sliced Wasserstein distance and narrow convergence of measures and quantize the approximation via empirical measures. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2307_05802 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Sliced Wasserstein distance between probability measures on Hilbert spaces Han, Ruiyu Metric Geometry Optimization and Control Probability 53B12 The sliced Wasserstein distance as well as its variants have been widely considered in comparing probability measures defined on $\mathbb R^d$. Here we derive the notion of sliced Wasserstein distance for measures on an infinite dimensional separable Hilbert spaces, depict the relation between sliced Wasserstein distance and narrow convergence of measures and quantize the approximation via empirical measures. |
| title | Sliced Wasserstein distance between probability measures on Hilbert spaces |
| topic | Metric Geometry Optimization and Control Probability 53B12 |
| url | https://arxiv.org/abs/2307.05802 |