Uniform ergodicity of geodesic slice sampling
Fuente:
arXiv
Enregistré dans:
| Auteur principal: | |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866912634915258368 |
|---|---|
| author | Hasenpflug, Mareike |
| author_facet | Hasenpflug, Mareike |
| contents | Geodesic slice sampling, introduced in Durmus et al., 2024, is a slice sampling based Markov chain Monte Carlo method for approximate sampling from distributions on Riemannian manifolds. We prove that it is uniformly ergodic for distributions with compact support that have a bounded density with respect to the Riemannian measure. The constants in our convergence bound are available explicitly, and we investigate their dependence on the hyperparameters of the geodesic slice sampler, the target distribution and the underlying domain. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_06748 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Uniform ergodicity of geodesic slice sampling Hasenpflug, Mareike Statistics Theory Probability 65C05 (Primary) 60J05, 53Z50 (Secondary) Geodesic slice sampling, introduced in Durmus et al., 2024, is a slice sampling based Markov chain Monte Carlo method for approximate sampling from distributions on Riemannian manifolds. We prove that it is uniformly ergodic for distributions with compact support that have a bounded density with respect to the Riemannian measure. The constants in our convergence bound are available explicitly, and we investigate their dependence on the hyperparameters of the geodesic slice sampler, the target distribution and the underlying domain. |
| title | Uniform ergodicity of geodesic slice sampling |
| topic | Statistics Theory Probability 65C05 (Primary) 60J05, 53Z50 (Secondary) |
| url | https://arxiv.org/abs/2510.06748 |