中文
相关论文

相关论文: Non-asymptotic analysis of Langevin-type Monte Car…

200 篇论文

This paper deals with Gibbs samplers that include high dimensional conditional Gaussian distributions. It proposes an efficient algorithm that avoids the high dimensional Gaussian sampling and relies on a random excursion along a small set…

统计计算 · 统计学 2016-04-20 Olivier Féron , François Orieux , Jean-François Giovannelli

Sampling from a lattice Gaussian distribution is emerging as an important problem in various areas such as coding and cryptography. The default sampling algorithm --- Klein's algorithm yields a distribution close to the lattice Gaussian…

信息论 · 计算机科学 2016-11-18 Zheng Wang , Cong Ling , Guillaume Hanrot

We study sampling problems associated with non-convex potentials that meanwhile lack smoothness. In particular, we consider target distributions that satisfy either logarithmic-Sobolev inequality or Poincar\'e inequality. Rather than…

机器学习 · 计算机科学 2023-02-21 Jiaming Liang , Yongxin Chen

We introduce a novel and efficient algorithm called the stochastic approximate gradient descent (SAGD), as an alternative to the stochastic gradient descent for cases where unbiased stochastic gradients cannot be trivially obtained.…

机器学习 · 计算机科学 2020-02-14 Yixuan Qiu , Xiao Wang

We propose a new method called the Metropolis-adjusted Mirror Langevin algorithm for approximate sampling from distributions whose support is a compact and convex set. This algorithm adds an accept-reject filter to the Markov chain induced…

统计计算 · 统计学 2024-06-24 Vishwak Srinivasan , Andre Wibisono , Ashia Wilson

Monte Carlo sampling techniques have broad applications in machine learning, Bayesian posterior inference, and parameter estimation. Often the target distribution takes the form of a product distribution over a dataset with a large number…

统计方法学 · 统计学 2019-09-19 Charles Matthews , Jonathan Weare

Discretization of continuous-time diffusion processes is a widely recognized method for sampling. However, it seems to be a considerable restriction when the potentials are often required to be smooth (gradient Lipschitz). This paper…

统计计算 · 统计学 2022-02-23 Dao Nguyen

We present an unbiased method for Bayesian posterior means based on kinetic Langevin dynamics that combines advanced splitting methods with enhanced gradient approximations. Our approach avoids Metropolis correction by coupling Markov…

统计计算 · 统计学 2025-12-04 Neil K. Chada , Benedict Leimkuhler , Daniel Paulin , Peter A. Whalley

We consider the problem of sampling from a target distribution, which is \emph {not necessarily logconcave}, in the context of empirical risk minimization and stochastic optimization as presented in Raginsky et al. (2017). Non-asymptotic…

统计理论 · 数学 2021-02-03 Ngoc Huy Chau , Éric Moulines , Miklos Rásonyi , Sotirios Sabanis , Ying Zhang

We propose a method for sampling from Gibbs distributions of the form $\pi(x)\propto\exp(-U(x))$ by considering a family $(\pi^{t})_t$ of approximations of the target density which is such that $\pi^{t}$ exhibits favorable properties for…

最优化与控制 · 数学 2025-10-10 Andreas Habring , Alexander Falk , Martin Zach , Thomas Pock

This work considers the problem of sampling from a probability distribution known up to a normalization constant while satisfying a set of statistical constraints specified by the expected values of general nonlinear functions. This problem…

机器学习 · 统计学 2025-01-08 Luiz F. O. Chamon , Mohammad Reza Karimi , Anna Korba

The Metropolis-adjusted Langevin algorithm (MALA) is a Metropolis-Hastings method for approximate sampling from continuous distributions. We derive upper bounds for the contraction rate in Kantorovich-Rubinstein-Wasserstein distance of the…

概率论 · 数学 2014-01-17 Andreas Eberle

We study the Riemannian Langevin Algorithm for the problem of sampling from a distribution with density $\nu$ with respect to the natural measure on a manifold with metric $g$. We assume that the target density satisfies a log-Sobolev…

机器学习 · 计算机科学 2022-04-25 Khashayar Gatmiry , Santosh S. Vempala

We study the problem of sampling from a probability distribution $\pi$ on $\rset^d$ which has a density \wrt\ the Lebesgue measure known up to a normalization factor $x \mapsto \rme^{-U(x)} / \int_{\rset^d} \rme^{-U(y)} \rmd y$. We analyze…

统计理论 · 数学 2019-09-17 M. Barkhagen , N. H. Chau , É. Moulines , M. Rásonyi , S. Sabanis , Y. Zhang

The randomized midpoint method, proposed by [SL19], has emerged as an optimal discretization procedure for simulating the continuous time Langevin diffusions. Focusing on the case of strong-convex and smooth potentials, in this paper, we…

机器学习 · 统计学 2021-09-14 Ye He , Krishnakumar Balasubramanian , Murat A. Erdogdu

In this work, we examine sampling problems with non-smooth potentials. We propose a novel Markov chain Monte Carlo algorithm for sampling from non-smooth potentials. We provide a non-asymptotical analysis of our algorithm and establish a…

机器学习 · 计算机科学 2022-02-11 Jiaming Liang , Yongxin Chen

We introduce a class of algorithms, termed proximal interacting particle Langevin algorithms (PIPLA), for inference and learning in latent variable models whose joint probability density is non-differentiable. Leveraging proximal Markov…

统计计算 · 统计学 2025-05-30 Paula Cordero Encinar , Francesca R. Crucinio , O. Deniz Akyildiz

We propose Decentralized Proximal Stochastic Gradient Langevin Dynamics (DE-PSGLD), a decentralized Markov chain Monte Carlo (MCMC) algorithm for sampling from a log-concave probability distribution constrained to a convex domain.…

机器学习 · 统计学 2026-05-04 Mohammad Rafiqul Islam , Lingjiong Zhu

This article considers the popular MCMC method of unadjusted Langevin Monte Carlo (LMC) and provides a non-asymptotic analysis of its sampling error in 2-Wasserstein distance. The proof is based on a refinement of mean-square analysis in Li…

机器学习 · 计算机科学 2022-02-22 Ruilin Li , Hongyuan Zha , Molei Tao

We propose a Markov chain Monte Carlo (MCMC) algorithm based on third-order Langevin dynamics for sampling from distributions with log-concave and smooth densities. The higher-order dynamics allow for more flexible discretization schemes,…

机器学习 · 统计学 2020-05-27 Wenlong Mou , Yi-An Ma , Martin J. Wainwright , Peter L. Bartlett , Michael I. Jordan