Accelerate Langevin Sampling with Birth-Death Process and Exploration Component

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Tan, Lezhi, Lu, Jianfeng
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915318596632576
author Tan, Lezhi
Lu, Jianfeng
author_facet Tan, Lezhi
Lu, Jianfeng
contents Sampling a probability distribution with known likelihood is a fundamental task in computational science and engineering. Aiming at multimodality, we propose a new sampling method that takes advantage of both birth-death process and exploration component. The main idea of this method is look before you leap. We keep two sets of samplers, one at warmer temperature and one at original temperature. The former one serves as pioneer in exploring new modes and passing useful information to the other, while the latter one samples the target distribution after receiving the information. We derive a mean-field limit and show how the exploration component accelerates the sampling process. Moreover, we prove exponential asymptotic convergence under mild assumption. Finally, we test on experiments from previous literature and compare our methodology to previous ones.
format Preprint
id arxiv_https___arxiv_org_abs_2305_05529
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Accelerate Langevin Sampling with Birth-Death Process and Exploration Component
Tan, Lezhi
Lu, Jianfeng
Computation
Machine Learning
Probability
Statistics Theory
65C05, 65C35, 60J80, 62F15
Sampling a probability distribution with known likelihood is a fundamental task in computational science and engineering. Aiming at multimodality, we propose a new sampling method that takes advantage of both birth-death process and exploration component. The main idea of this method is look before you leap. We keep two sets of samplers, one at warmer temperature and one at original temperature. The former one serves as pioneer in exploring new modes and passing useful information to the other, while the latter one samples the target distribution after receiving the information. We derive a mean-field limit and show how the exploration component accelerates the sampling process. Moreover, we prove exponential asymptotic convergence under mild assumption. Finally, we test on experiments from previous literature and compare our methodology to previous ones.
title Accelerate Langevin Sampling with Birth-Death Process and Exploration Component
topic Computation
Machine Learning
Probability
Statistics Theory
65C05, 65C35, 60J80, 62F15
url https://arxiv.org/abs/2305.05529