Parallelized Midpoint Randomization for Langevin Monte Carlo
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916555162386432 |
|---|---|
| author | Yu, Lu Dalalyan, Arnak |
| author_facet | Yu, Lu Dalalyan, Arnak |
| contents | We study the problem of sampling from a target probability density function in frameworks where parallel evaluations of the log-density gradient are feasible. Focusing on smooth and strongly log-concave densities, we revisit the parallelized randomized midpoint method and investigate its properties using recently developed techniques for analyzing its sequential version. Through these techniques, we derive upper bounds on the Wasserstein distance between sampling and target densities. These bounds quantify the substantial runtime improvements achieved through parallel processing. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_14434 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Parallelized Midpoint Randomization for Langevin Monte Carlo Yu, Lu Dalalyan, Arnak Statistics Theory Machine Learning Probability Computation We study the problem of sampling from a target probability density function in frameworks where parallel evaluations of the log-density gradient are feasible. Focusing on smooth and strongly log-concave densities, we revisit the parallelized randomized midpoint method and investigate its properties using recently developed techniques for analyzing its sequential version. Through these techniques, we derive upper bounds on the Wasserstein distance between sampling and target densities. These bounds quantify the substantial runtime improvements achieved through parallel processing. |
| title | Parallelized Midpoint Randomization for Langevin Monte Carlo |
| topic | Statistics Theory Machine Learning Probability Computation |
| url | https://arxiv.org/abs/2402.14434 |