中文
相关论文

相关论文: Convergence rate and concentration inequalities fo…

200 篇论文

The functional characterization of a measure, an essential but delicate aspect of Stein's method, is shown to be accessible for stable probability distributions on convex cones. This notion encompasses the usual stable distributions…

概率论 · 数学 2026-04-02 Costacèque , Decreusefond

We propose a Monte Carlo algorithm to sample from high dimensional probability distributions that combines Markov chain Monte Carlo and importance sampling. We provide a careful theoretical analysis, including guarantees on robustness to…

统计计算 · 统计学 2019-09-18 Giacomo Zanella , Gareth Roberts

We consider the problem of inference in discrete probabilistic models, that is, distributions over subsets of a finite ground set. These encompass a range of well-known models in machine learning, such as determinantal point processes and…

机器学习 · 计算机科学 2018-07-10 Alkis Gotovos , Hamed Hassani , Andreas Krause , Stefanie Jegelka

We investigate the complexity of covariance matrix estimation for Gibbs distributions based on dependent samples from a Markov chain. We show that when $\pi$ satisfies a Poincar\'e inequality and the chain possesses a spectral gap, we can…

统计理论 · 数学 2024-10-23 Yunbum Kook , Matthew S. Zhang

Bayesian networks offer great potential for use in automating large scale diagnostic reasoning tasks. Gibbs sampling is the main technique used to perform diagnostic reasoning in large richly interconnected Bayesian networks. Unfortunately…

人工智能 · 计算机科学 2013-02-21 Mark Hulme

Sampling from matrix generalized inverse Gaussian (MGIG) distributions is required in Markov Chain Monte Carlo (MCMC) algorithms for a variety of statistical models. However, an efficient sampling scheme for the MGIG distributions has not…

统计方法学 · 统计学 2023-11-08 Yasuyuki Hamura , Kaoru Irie , Shonosuke Sugasawa

The particle Gibbs sampler is a Markov chain Monte Carlo (MCMC) algorithm to sample from the full posterior distribution of a state-space model. It does so by executing Gibbs sampling steps on an extended target distribution defined on the…

统计计算 · 统计学 2015-07-29 Nicolas Chopin , Sumeetpal S. Singh

One of the most demanding calculations is to generate random samples from a specified probability distribution (usually with an unknown normalizing prefactor) in a high-dimensional configuration space. One often has to resort to using a…

计算物理 · 物理学 2015-06-18 Youhan Fang , Jesus-Maria Sanz-Serna , Robert D. Skeel

Markov chain Monte Calro methods (MCMC) are commonly used in Bayesian statistics. In the last twenty years, many results have been established for the calculation of the exact convergence rate of MCMC methods. We introduce another rate of…

统计理论 · 数学 2014-02-17 Kengo Kamatani

We extend recent higher order concentration results in the discrete setting to include functions of possibly dependent variables whose distribution (on the product space) satisfies a logarithmic Sobolev inequality with respect to a…

概率论 · 数学 2020-05-15 Friedrich Götze , Holger Sambale , Arthur Sinulis

We give the first rigorous proof of the convergence of Riemannian Hamiltonian Monte Carlo, a general (and practical) method for sampling Gibbs distributions. Our analysis shows that the rate of convergence is bounded in terms of natural…

数据结构与算法 · 计算机科学 2017-10-18 Yin Tat Lee , Santosh S. Vempala

In this paper, we analyze the convergence rate of a collapsed Gibbs sampler for crossed random effects models. Our results apply to a substantially larger range of models than previous works, including models that incorporate missingness…

统计计算 · 统计学 2021-10-22 Swarnadip Ghosh , Chenyang Zhong

We use a non-Markovian coupling and small modifications of techniques from the theory of finite Markov chains to analyze some Markov chains on continuous state spaces. The first is a Gibbs sampler on narrow contingency tables, the second a…

概率论 · 数学 2016-11-25 Aaron Smith

Cognitive diagnosis models (CDMs) are useful statistical tools to provide rich information relevant for intervention and learning. As a popular approach to estimate and make inference of CDMs, the Markov chain Monte Carlo (MCMC) algorithm…

统计方法学 · 统计学 2021-02-16 Juntao Wang , Ningzhong Shi , Xue Zhang , Gongjun Xu

This chapter surveys the most standard Monte Carlo methods available for simulating from a posterior distribution associated with a mixture and conducts some experiments about the robustness of the Gibbs sampler in high dimensional Gaussian…

We consider local Markov chain Monte-Carlo algorithms for sampling from the weighted distribution of independent sets with activity $\l$, where the weight of an independent set $I$ is $\l^{|I|}$. A recent result has established that Gibbs…

概率论 · 数学 2007-05-23 Elchanan Mossel , Dror Weitz , Nicholas Wormald

The paper presents efficient approaches for evaluating convergence rate in total variation for finite and general linear Markov chains. The motivation for studying convergence rate in this metric is its usefulness in various limit theorems.…

概率论 · 数学 2026-01-21 Alexander Veretennikov

Gibbs measures, such as Coulomb gases, are popular in modelling systems of interacting particles. Recently, we proposed to use Gibbs measures as randomized numerical integration algorithms with respect to a target measure $\pi$ on $\mathbb…

机器学习 · 计算机科学 2025-08-05 Rémi Bardenet , Mylène Maïda , Martin Rouault

Importance sampling is a Monte Carlo technique for efficiently estimating the likelihood of rare events by biasing the sampling distribution towards the rare event of interest. By drawing weighted samples from a learned proposal…

机器学习 · 统计学 2025-05-20 Liam A. Kruse , Marc R. Schlichting , Mykel J. Kochenderfer

We present a new method for conducting Monte Carlo inference in graphical models which combines explicit search with generalized importance sampling. The idea is to reduce the variance of importance sampling by searching for significant…

机器学习 · 计算机科学 2013-01-18 Dale Schuurmans , Finnegan Southey