paper-with-me

홈 › Papers

Non-Reversible Langevin Algorithms for Constrained Sampling

2025-01-20 · Hengrong Du, Qi Feng, Changwei Tu, Xiaoyu Wang, Lingjiong Zhu

We consider the constrained sampling problem where the goal is to sample from a target distribution on a constrained domain. We propose skew-reflected non-reversible Langevin dynamics (SRNLD), a continuous-time stochastic differential equation with skew-reflected boundary. We obtain non-asymptotic convergence rate of SRNLD to the target distribution in both total variation and 1-Wasserstein distances. By breaking reversibility, we show that the convergence is faster than the special case of the reversible dynamics. Based on the discretization of SRNLD, we propose skew-reflected non-reversible Langevin Monte Carlo (SRNLMC), and obtain non-asymptotic discretization error from SRNLD, and convergence guarantees to the target distribution in 1-Wasserstein distance. We show better performance guarantees than the projected Langevin Monte Carlo in the literature that is based on the reversible dynamics. Numerical experiments are provided for both synthetic and real datasets to show efficiency of the proposed algorithms.

📄 PDF Abstract BibTeX arXiv:2501.11743

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

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…

Breaking Reversibility Accelerates Langevin Dynamics for Global Non-Convex Optimization

2018-12-19 · Xuefeng Gao, Mert Gurbuzbalaban, Lingjiong Zhu

Langevin dynamics (LD) has been proven to be a powerful technique for optimizing a non-convex objective as an efficient algorithm to find local minima while eventually visiting a global minimum on longer time-scales. LD …

Faster Convergence of Stochastic Gradient Langevin Dynamics for Non-Log-Concave Sampling

2020-10-19 · Difan Zou, Pan Xu, Quanquan Gu

We provide a new convergence analysis of stochastic gradient Langevin dynamics (SGLD) for sampling from a class of distributions that can be non-log-concave. At the core of our approach is a novel conductance analysis of…

Breaking Reversibility Accelerates Langevin Dynamics for Non-Convex Optimization

2020-12-01 · NeurIPS 2020 12 · Xuefeng Gao, Mert Gurbuzbalaban, Lingjiong Zhu

Langevin dynamics (LD) has been proven to be a powerful technique for optimizing a non-convex objective as an efficient algorithm to find local minima while eventually visiting a global minimum on longer time-scales. LD …

Constrained Langevin Algorithms with L-mixing External Random Variables

2022-05-27 · Yuping Zheng, Andrew Lamperski

Langevin algorithms are gradient descent methods augmented with additive noise, and are widely used in Markov Chain Monte Carlo (MCMC) sampling, optimization, and machine learning. In recent years, the non-asymptotic ana…