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 study the problem of sampling from log-concave distributions supported on convex, compact sets, with a particular focus on the randomized midpoint discretization of both vanilla and kinetic Langevin diffusions in this…

机器学习 · 统计学 2025-05-27 Yifeng Yu , Lu Yu

The task of sampling from a high-dimensional distribution $\pi$ on $\R^d$ is a fundamental algorithmic problem with applications throughout statistics, engineering, and the sciences. Consider the Langevin diffusion on $\R^d$ \begin{align*}…

统计理论 · 数学 2025-11-18 Tian Shen , Zhonggen Su

We consider the problem of sampling distributions stemming from non-convex potentials with Unadjusted Langevin Algorithm (ULA). We prove the stability of the discrete-time ULA to drift approximations under the assumption that the potential…

机器学习 · 统计学 2025-09-01 Marien Renaud , Valentin De Bortoli , Arthur Leclaire , Nicolas Papadakis

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…

机器学习 · 计算机科学 2025-04-16 Hengrong Du , Qi Feng , Changwei Tu , Xiaoyu Wang , Lingjiong Zhu

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

Recent studies on diffusion-based sampling methods have shown that Langevin Monte Carlo (LMC) algorithms can be beneficial for non-convex optimization, and rigorous theoretical guarantees have been proven for both asymptotic and finite-time…

最优化与控制 · 数学 2019-01-23 Thanh Huy Nguyen , Umut Şimşekli , Gaël Richard

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

We establish a systematic framework of unbiased quantum sampling and estimation protocols for the classical Gibbs expectation. This framework generalizes existing approaches to the partition function estimation and has broader applications…

量子物理 · 物理学 2026-04-02 Xinmiao Li , Jin-Peng Liu

A canonical algorithm for log-concave sampling is the Langevin Algorithm, aka the Langevin Diffusion run with some discretization stepsize $\eta > 0$. This discretization leads the Langevin Algorithm to have a stationary distribution…

机器学习 · 统计学 2024-10-22 Jason M. Altschuler , Kunal Talwar

The problem of generating random samples of high-dimensional posterior distributions is considered. The main results consist of non-asymptotic computational guarantees for Langevin-type MCMC algorithms which scale polynomially in key…

统计理论 · 数学 2022-03-25 Richard Nickl , Sven Wang

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 SGLD using an…

机器学习 · 计算机科学 2021-02-24 Difan Zou , Pan Xu , Quanquan Gu

We propose and study a new multilevel method for the numerical approximation of a Gibbs distribution $\pi$ on $\mathbb{R}^d$, based on (overdamped) Langevin diffusions. This method inspired by \cite{mainPPlangevin} and…

数值分析 · 数学 2024-02-13 Maxime Egéa , Fabien Panloup

This paper introduces and analyses interacting underdamped Langevin algorithms, termed Kinetic Interacting Particle Langevin Monte Carlo (KIPLMC) methods, for statistical inference in latent variable models. We propose a diffusion process…

统计计算 · 统计学 2026-04-17 Paul Felix Valsecchi Oliva , O. Deniz Akyildiz

Error bounds are derived for sampling and estimation using a discretization of an intrinsically defined Langevin diffusion with invariant measure $\text{d}\mu_\phi \propto e^{-\phi} \mathrm{dvol}_g $ on a compact Riemannian manifold. Two…

统计理论 · 数学 2025-12-10 Karthik Bharath , Alexander Lewis , Akash Sharma , Michael V Tretyakov

We present an optimization algorithm that can identify a global minimum of a potentially nonconvex smooth function with high probability, assuming the Gibbs measure of the potential satisfies a logarithmic Sobolev inequality. Our…

最优化与控制 · 数学 2025-09-16 Daniel Cortild , Claire Delplancke , Nadia Oudjane , Juan Peypouquet

Langevin diffusions are rapidly convergent under appropriate functional inequality assumptions. Hence, it is natural to expect that with additional smoothness conditions to handle the discretization errors, their discretizations like the…

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

Approximate Thompson sampling with Langevin Monte Carlo broadens its reach from Gaussian posterior sampling to encompass more general smooth posteriors. However, it still encounters scalability issues in high-dimensional problems when…

机器学习 · 统计学 2024-06-24 Haoyang Zheng , Wei Deng , Christian Moya , Guang Lin

A new methodology is presented for the construction of control variates to reduce the variance of additive functionals of Markov Chain Monte Carlo (MCMC) samplers. Our control variates are definedthrough the minimization of the asymptotic…

统计方法学 · 统计学 2019-07-09 Nicolas Brosse , Alain Durmus , Sean Meyn , Eric Moulines , Anand Radhakrishnan

A key task in Bayesian statistics is sampling from distributions that are only specified up to a partition function (i.e., constant of proportionality). However, without any assumptions, sampling (even approximately) can be #P-hard, and few…

机器学习 · 计算机科学 2018-12-03 Rong Ge , Holden Lee , Andrej Risteski