Lévy Langevin Monte Carlo for sampling from heavy-tailed target distributions
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_ | 1866916843012227072 |
|---|---|
| author | Behme, Anita Schwienhorst, Claudius Lütke |
| author_facet | Behme, Anita Schwienhorst, Claudius Lütke |
| contents | We extend the Lévy Langevin Monte Carlo method studied by Oechsler in 2024 to the setting of a target distribution with heavy tails: Choosing a target distribution from the class of subexponential distributions we prove convergence of a solution of a stochastic differential equation to this target. Hereby, the stochastic differential equation is driven by a compound Poisson process - unlike in the case of a classical Langevin diffusion. The method allows one to sample from non-smooth targets and distributions with separated modes with exponential convergence to the invariant distribution, which in general cannot be guaranteed by the classical Langevin diffusion in presence of heavy tails. The method is promising due to the possibility of a simple implementation because of the compound Poisson noise term. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_10320 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Lévy Langevin Monte Carlo for sampling from heavy-tailed target distributions Behme, Anita Schwienhorst, Claudius Lütke Probability 60G51, 60H10, 60G10 (primary), 65C05 (secondary) We extend the Lévy Langevin Monte Carlo method studied by Oechsler in 2024 to the setting of a target distribution with heavy tails: Choosing a target distribution from the class of subexponential distributions we prove convergence of a solution of a stochastic differential equation to this target. Hereby, the stochastic differential equation is driven by a compound Poisson process - unlike in the case of a classical Langevin diffusion. The method allows one to sample from non-smooth targets and distributions with separated modes with exponential convergence to the invariant distribution, which in general cannot be guaranteed by the classical Langevin diffusion in presence of heavy tails. The method is promising due to the possibility of a simple implementation because of the compound Poisson noise term. |
| title | Lévy Langevin Monte Carlo for sampling from heavy-tailed target distributions |
| topic | Probability 60G51, 60H10, 60G10 (primary), 65C05 (secondary) |
| url | https://arxiv.org/abs/2507.10320 |