中文
相关论文

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

200 篇论文

In this paper, we provide non-asymptotic upper bounds on the error of sampling from a target density using three schemes of discretized Langevin diffusions. The first scheme is the Langevin Monte Carlo (LMC) algorithm, the Euler…

统计理论 · 数学 2021-12-07 Arnak S. Dalalyan , Avetik Karagulyan , Lionel Riou-Durand

We propose efficient Langevin Monte Carlo algorithms for sampling distributions with nonsmooth convex composite potentials, which is the sum of a continuously differentiable function and a possibly nonsmooth function. We devise such…

机器学习 · 统计学 2022-07-12 Tim Tsz-Kit Lau , Han Liu

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 analysis of Langevin…

机器学习 · 计算机科学 2023-01-10 Yuping Zheng , Andrew Lamperski

Langevin algorithms are gradient descent methods with additive noise. They have been used for decades in Markov chain Monte Carlo (MCMC) sampling, optimization, and learning. Their convergence properties for unconstrained non-convex…

机器学习 · 计算机科学 2020-12-23 Andrew Lamperski

In this work, we will establish that the Langevin Monte-Carlo algorithm can learn depth-2 neural nets of any size and for any data and we give non-asymptotic convergence rates for it. We achieve this via showing that in q-Renyi divergence,…

机器学习 · 计算机科学 2025-08-20 Dibyakanti Kumar , Samyak Jha , Anirbit Mukherjee

We provide convergence guarantees in Wasserstein distance for a variety of variance-reduction methods: SAGA Langevin diffusion, SVRG Langevin diffusion and control-variate underdamped Langevin diffusion. We analyze these methods under a…

Sampling from various kinds of distributions is an issue of paramount importance in statistics since it is often the key ingredient for constructing estimators, test procedures or confidence intervals. In many situations, the exact sampling…

统计计算 · 统计学 2016-12-06 Arnak S. Dalalyan

Motivated by applications to deep learning which often fail standard Lipschitz smoothness requirements, we examine the problem of sampling from distributions that are not log-concave and are only weakly dissipative, with log-gradients…

机器学习 · 统计学 2024-05-29 Iosif Lytras , Panayotis Mertikopoulos

In order to solve tasks like uncertainty quantification or hypothesis tests in Bayesian imaging inverse problems, we often have to draw samples from the arising posterior distribution. For the usually log-concave but high-dimensional…

统计计算 · 统计学 2025-01-23 Matthias J. Ehrhardt , Lorenz Kuger , Carola-Bibiane Schönlieb

A new (unadjusted) Langevin Monte Carlo (LMC) algorithm with improved rates in total variation and in Wasserstein distance is presented. All these are obtained in the context of sampling from a target distribution $\pi$ that has a density…

统计理论 · 数学 2019-10-18 Sotirios Sabanis , Ying Zhang

Langevin diffusion processes and their discretizations are often used for sampling from a target density. The most convenient framework for assessing the quality of such a sampling scheme corresponds to smooth and strongly log-concave…

概率论 · 数学 2018-12-27 Arnak S. Dalalyan , Lionel Riou-Durand

We revisit the problem of sampling from a target distribution that has a smooth strongly log-concave density everywhere in $\mathbb R^p$. In this context, if no additional density information is available, the randomized midpoint…

统计理论 · 数学 2023-06-19 Lu Yu , Avetik Karagulyan , Arnak Dalalyan

Discretization of continuous-time diffusion processes is a widely recognized method for sampling. However, the canonical Euler Maruyama discretization of the Langevin diffusion process, referred as Unadjusted Langevin Algorithm (ULA),…

统计计算 · 统计学 2021-07-28 Dao Nguyen , Xin Dang , Yixin Chen

In this article we consider sampling from log concave distributions in Hamiltonian setting, without assuming that the objective gradient is globally Lipschitz. We propose two algorithms based on monotone polygonal (tamed) Euler schemes, to…

概率论 · 数学 2023-01-20 Tim Johnston , Iosif Lytras , Sotirios Sabanis

We study a sequential Monte Carlo algorithm to sample from the Gibbs measure with a non-convex energy function at a low temperature. We use the practical and popular geometric annealing schedule, and use a Langevin diffusion at each…

统计理论 · 数学 2026-01-13 Ruiyu Han , Gautam Iyer , Dejan Slepčev

Sampling from various kinds of distributions is an issue of paramount importance in statistics since it is often the key ingredient for constructing estimators, test procedures or confidence intervals. In many situations, the exact sampling…

统计理论 · 数学 2018-11-05 Avetik Karagulyan

Langevin Monte Carlo (LMC) and its stochastic gradient versions are powerful algorithms for sampling from complex high-dimensional distributions. To sample from a distribution with density $\pi(\theta)\propto \exp(-U(\theta)) $, LMC…

统计计算 · 统计学 2023-09-25 Sifan Liu

The problem of sampling according to the probability distribution minimizing a given free energy, using interacting particles unadjusted kinetic Langevin Monte Carlo, is addressed. In this setting, three sources of error arise, related to…

概率论 · 数学 2024-12-05 Pierre Monmarché , Katharina Schuh

In this paper, we focus on non-asymptotic bounds related to the Euler scheme of an ergodic diffusion with a possibly multiplicative diffusion term (non-constant diffusion coefficient). More precisely, the objective of this paper is to…

概率论 · 数学 2022-09-23 Gilles Pages , Fabien Panloup

We propose and analyze a class of adaptive sampling algorithms for multimodal distributions on a bounded domain, which share a structural resemblance to the classic overdamped Langevin dynamics. We first demonstrate that this class of…

机器学习 · 计算机科学 2024-11-26 Björn Engquist , Kui Ren , Yunan Yang