中文
相关论文

相关论文: Efficient Sampling on Riemannian Manifolds via Lan…

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

We study sampling from a target distribution $\nu_* = e^{-f}$ using the unadjusted Langevin Monte Carlo (LMC) algorithm when the potential $f$ satisfies a strong dissipativity condition and it is first-order smooth with a Lipschitz…

机器学习 · 统计学 2021-07-09 Murat A. Erdogdu , Rasa Hosseinzadeh , Matthew S. Zhang

This paper presents a detailed theoretical analysis of the Langevin Monte Carlo sampling algorithm recently introduced in Durmus et al. (Efficient Bayesian computation by proximal Markov chain Monte Carlo: when Langevin meets Moreau, 2016)…

统计方法学 · 统计学 2017-05-26 Nicolas Brosse , Alain Durmus , Éric Moulines , Marcelo Pereyra

Low-dimensional structure in real-world data plays an important role in the success of generative models, which motivates diffusion models defined on intrinsic data manifolds. Such models are driven by stochastic differential equations…

机器学习 · 统计学 2026-03-05 Zhiyuan Zhan , Masashi Sugiyama

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

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 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

We consider in this paper the problem of sampling a high-dimensional probability distribution $\pi$ having a density with respect to the Lebesgue measure on $\mathbb{R}^d$, known up to a normalization constant $x \mapsto \pi(x)=…

统计理论 · 数学 2018-07-17 Alain Durmus , Eric Moulines

Performing exact Bayesian inference for complex models is computationally intractable. Markov chain Monte Carlo (MCMC) algorithms can provide reliable approximations of the posterior distribution but are expensive for large datasets and…

统计计算 · 统计学 2021-12-09 Maxime Vono , Daniel Paulin , Arnaud Doucet

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 Markov chain Monte…

机器学习 · 统计学 2024-05-30 Tim Tsz-Kit Lau , Han Liu , Thomas Pock

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…

Bayesian inference for doubly-intractable pairwise exponential graphical models typically involves variations of the exchange algorithm or approximate Markov chain Monte Carlo (MCMC) samplers. However, existing methods for both classes of…

统计计算 · 统计学 2026-03-30 Yujie Chen , Antik Chakraborty , Anindya Bhadra

The resolution of many large-scale inverse problems using MCMC methods requires a step of drawing samples from a high dimensional Gaussian distribution. While direct Gaussian sampling techniques, such as those based on Cholesky…

统计方法学 · 统计学 2015-06-22 Clément Gilavert , Saïd Moussaoui , Jérôme Idier

Sampling from distributions play a crucial role in aiding practitioners with statistical inference. However, in numerous situations, obtaining exact samples from complex distributions is infeasible. Consequently, researchers often turn to…

统计计算 · 统计学 2024-04-01 Riddhiman Bhattacharya , Tiefeng Jiang

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

Underdamped Langevin Monte Carlo (ULMC) is an algorithm used to sample from unnormalized densities by leveraging the momentum of a particle moving in a potential well. We provide a novel analysis of ULMC, motivated by two central questions:…

Markov chain Monte Carlo (MCMC) methods are fundamental to Bayesian computation, but can be computationally intensive, especially in high-dimensional settings. Push-forward generative models, such as generative adversarial networks (GANs),…

机器学习 · 计算机科学 2026-02-25 Jonathan Spence , Tobías I. Liaudat , Konstantinos Zygalakis , Marcelo Pereyra

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

We consider the outstanding problem of sampling from an unnormalized density that may be non-log-concave and multimodal. To enhance the performance of simple Markov chain Monte Carlo (MCMC) methods, techniques of annealing type have been…

机器学习 · 统计学 2025-02-18 Wei Guo , Molei Tao , Yongxin Chen