paper-with-me

Papers

Accelerating Langevin Monte Carlo Sampling: A Large Deviations Analysis

2025-03-24 · Nian Yao, Pervez Ali, Xihua Tao, Lingjiong Zhu

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.

📄 PDF Abstract BibTeX arXiv:2503.19066

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Accelerating Approximate Thompson Sampling with Underdamped Langevin Monte Carlo

2024-01-22 · Haoyang Zheng, Wei Deng, Christian Moya, Guang Lin

Approximate Thompson sampling with Langevin Monte Carlo broadens its reach from Gaussian posterior sampling to encompass more general smooth posteriors. However, it still encounters scalability issues in high-dimensional…

Thompson Sampling

Subspace Langevin Monte Carlo

2024-12-18 · Tyler Maunu, Jiayi Yao

Sampling from high-dimensional distributions has wide applications in data science and machine learning but poses significant computational challenges. We introduce Subspace Langevin Monte Carlo (SLMC), a novel and effic…

Computational Efficiency

Accelerating Constrained Sampling: A Large Deviations Approach

2025-06-09 · Yingli Wang, Changwei Tu, Xiaoyu Wang, Lingjiong Zhu

The problem of sampling a target probability distribution on a constrained domain arises in many applications including machine learning. For constrained sampling, various Langevin algorithms such as projected Langevin M…

Non-Log-Concave and Nonsmooth Sampling via Langevin Monte Carlo Algorithms

2023-05-25 · Tim Tsz-Kit Lau, Han Liu, Thomas Pock

We study the problem of approximate sampling from non-log-concave distributions, e.g., Gaussian mixtures, which is often challenging even in low dimensions due to their multimodality. We focus on performing this task via…

Bayesian InferenceImage Deconvolution

High-Order Langevin Monte Carlo Algorithms

2025-08-24 · Thanh Dang, Mert Gurbuzbalaban, Mohammad Rafiqul Islam, Nian Yao 외 arxiv

Langevin algorithms are popular Markov chain Monte Carlo (MCMC) methods for large-scale sampling problems that often arise in data science. We propose Monte Carlo algorithms based on the discretizations of $P$-th order L…