Accelerating Langevin Monte Carlo Sampling: A Large Deviations Analysis
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910240128106496 |
|---|---|
| author | Yao, Nian Ali, Pervez Tao, Xihua Zhu, Lingjiong |
| author_facet | Yao, Nian Ali, Pervez Tao, Xihua Zhu, Lingjiong |
| contents | Langevin algorithms are popular Markov chain Monte Carlo methods that are often used to solve high-dimensional large-scale sampling problems in machine learning. The most classical Langevin Monte Carlo algorithm is based on the overdamped Langevin dynamics. There are many variants of Langevin dynamics that often show superior performance in practice. In this paper, we provide a unified approach to study the acceleration of the variants of the overdamped Langevin dynamics through the lens of large deviations theory. Numerical experiments using both synthetic and real data are provided to illustrate the efficiency of these variants. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_19066 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Accelerating Langevin Monte Carlo Sampling: A Large Deviations Analysis Yao, Nian Ali, Pervez Tao, Xihua Zhu, Lingjiong Probability Machine Learning Langevin algorithms are popular Markov chain Monte Carlo methods that are often used to solve high-dimensional large-scale sampling problems in machine learning. The most classical Langevin Monte Carlo algorithm is based on the overdamped Langevin dynamics. There are many variants of Langevin dynamics that often show superior performance in practice. In this paper, we provide a unified approach to study the acceleration of the variants of the overdamped Langevin dynamics through the lens of large deviations theory. Numerical experiments using both synthetic and real data are provided to illustrate the efficiency of these variants. |
| title | Accelerating Langevin Monte Carlo Sampling: A Large Deviations Analysis |
| topic | Probability Machine Learning |
| url | https://arxiv.org/abs/2503.19066 |