中文
相关论文

相关论文: Convergence of Langevin MCMC in KL-divergence

200 篇论文

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

Langevin Monte Carlo (LMC) is an iterative algorithm used to generate samples from a distribution that is known only up to a normalizing constant. The nonasymptotic dependence of its mixing time on the dimension and target accuracy is…

We study the underdamped Langevin diffusion when the log of the target distribution is smooth and strongly concave. We present a MCMC algorithm based on its discretization and show that it achieves $\varepsilon$ error (in 2-Wasserstein…

机器学习 · 统计学 2018-01-30 Xiang Cheng , Niladri S. Chatterji , Peter L. Bartlett , Michael I. Jordan

We propose a new discretization of the mirror-Langevin diffusion and give a crisp proof of its convergence. Our analysis uses relative convexity/smoothness and self-concordance, ideas which originated in convex optimization, together with a…

统计理论 · 数学 2021-10-26 Kwangjun Ahn , Sinho Chewi

We study the problem of sampling from a distribution $p^*(x) \propto \exp\left(-U(x)\right)$, where the function $U$ is $L$-smooth everywhere and $m$-strongly convex outside a ball of radius $R$, but potentially nonconvex inside this ball.…

In this paper, we investigate a continuous time version of the Stochastic Langevin Monte Carlo method, introduced in [WT11], that incorporates a stochastic sampling step inside the traditional over-damped Langevin diffusion. This method is…

机器学习 · 统计学 2023-01-10 Marelys Crespo Navas , Sébastien Gadat , Xavier Gendre

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

Discretization of continuous-time diffusion processes is a widely recognized method for sampling. However, the canonical Euler-Maruyama discretization of the Langevin diffusion process, also named as Langevin Monte Carlo (LMC), studied…

统计计算 · 统计学 2020-10-06 Anh Duc Doan , Xin Dang , Dao Nguyen

Classically, the continuous-time Langevin diffusion converges exponentially fast to its stationary distribution $\pi$ under the sole assumption that $\pi$ satisfies a Poincar\'e inequality. Using this fact to provide guarantees for the…

统计理论 · 数学 2024-07-11 Sinho Chewi , Murat A. Erdogdu , Mufan Bill Li , Ruoqi Shen , Matthew Zhang

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

It is known that gradient-based MCMC samplers for continuous spaces, such as Langevin Monte Carlo (LMC), can be derived as particle versions of a gradient flow that minimizes KL divergence on a Wasserstein manifold. The superior efficiency…

机器学习 · 计算机科学 2023-02-24 Haoran Sun , Hanjun Dai , Bo Dai , Haomin Zhou , Dale Schuurmans

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

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

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

We extend the Langevin Monte Carlo (LMC) algorithm to compactly supported measures via a projection step, akin to projected Stochastic Gradient Descent (SGD). We show that (projected) LMC allows to sample in polynomial time from a…

概率论 · 数学 2016-08-08 Sébastien Bubeck , Ronen Eldan , Joseph Lehec

Sampling from log-concave distributions is a well researched problem that has many applications in statistics and machine learning. We study the distributions of the form $p^{*}\propto\exp(-f(x))$, where…

机器学习 · 计算机科学 2019-09-13 Ruoqi Shen , Yin Tat Lee

The stochastic gradient Langevin Dynamics is one of the most fundamental algorithms to solve sampling problems and non-convex optimization appearing in several machine learning applications. Especially, its variance reduced versions have…

机器学习 · 计算机科学 2022-11-22 Yuri Kinoshita , Taiji Suzuki

In this paper, we study the problem of sampling from distributions of the form p(x) \propto e^{-\beta f(x)} for some function f whose values and gradients we can query. This mode of access to f is natural in the scenarios in which such…

概率论 · 数学 2020-09-22 Ankur Moitra , Andrej Risteski

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

Langevin Dynamics is a Stochastic Differential Equation (SDE) central to sampling and generative modeling and is implemented via time discretization. Langevin Monte Carlo (LMC), based on the Euler-Maruyama discretization, is the simplest…

机器学习 · 计算机科学 2025-10-10 Saravanan Kandasamy , Dheeraj Nagaraj
‹ 上一页 1 2 3 10 下一页 ›