Convergence rate and concentration inequalities for Gibbs sampling in high dimension
From MaRDI portal
(Redirected from Publication:470046)
Abstract: The objective of this paper is to study the Gibbs sampling for computing the mean of observable in very high dimension - a powerful Markov chain Monte Carlo method. Under the Dobrushin's uniqueness condition, we establish some explicit and sharp estimate of the exponential convergence rate and prove some Gaussian concentration inequalities for the empirical mean.
Recommendations
- scientific article; zbMATH DE number 1191611
- Convergence rate of Gibbs sampler and its application
- On convergence rates of Gibbs samplers for uniform distributions
- Rates of convergence for Gibbs sampling for variance component models
- Rate of convergence of the Gibbs sampler in the Gaussian case
- Rates of convergence for Gibbs sampling in the analysis of almost exchangeable data
- Convergence rates for a hierarchical Gibbs sampler
Cites work
- scientific article; zbMATH DE number 3909121 (Why is no real title available?)
- scientific article; zbMATH DE number 706329 (Why is no real title available?)
- scientific article; zbMATH DE number 1909499 (Why is no real title available?)
- scientific article; zbMATH DE number 1405932 (Why is no real title available?)
- scientific article; zbMATH DE number 1418384 (Why is no real title available?)
- scientific article; zbMATH DE number 3294019 (Why is no real title available?)
- A large deviation approach to some transportation cost inequalities
- A measure concentration inequality for contracting Markov chains
- Approach to equilibrium of Glauber dynamics in the one phase region. I: The attractive case
- Bounding \(\bar d\)-distance by informational divergence: A method to prove measure concentration
- Concentration of measure inequalities for Markov chains and \(\Phi\)-mixing processes.
- Curvature, concentration and error estimates for Markov chain Monte Carlo
- Dobrushin uniqueness theorem and logarithmic Sobolev inequalities
- Exponential integrability and transportation cost related to logarithmic Sobolev inequalities
- General state space Markov chains and MCMC algorithms
- Gibbs sampling, conjugate priors and coupling
- Gibbs sampling, exponential families and orthogonal polynomials
- Inégalités de Hoeffding pour les fonctions lipschitziennes de suites dépendantes
- Markov chains and stochastic stability
- Measure concentration and strong mixing
- Measure concentration for Euclidean distance in the case of dependent random variables.
- Minorization Conditions and Convergence Rates for Markov Chain Monte Carlo
- Poincaré and transportation inequalities for Gibbs measures under the Dobrushin uniqueness condition
- Prescribing a System of Random Variables by Conditional Distributions
- Quantitative convergence rates of Markov chains: A simple account
- Sequential Monte Carlo Methods in Practice
- The concentration of measure phenomenon
- Transport Inequalities. A Survey
- Transportation cost for Gaussian and other product measures
- Transportation cost-information inequalities and applications to random dynamical systems and diffusions.
- Weak transport inequalities and applications to exponential and oracle inequalities
- Yet Another Look at Harris’ Ergodic Theorem for Markov Chains
Cited in
(13)- Spectral telescope: convergence rate bounds for random-scan Gibbs samplers based on a hierarchical structure
- Convergence rates of the blocked Gibbs sampler with random scan in the Wasserstein metric
- Strong replica symmetry for high-dimensional disordered log-concave Gibbs measures
- Convergence rates of Gibbs measures with degenerate minimum
- Concentration inequalities for Gibbs sampling under \(d_{l_{2}}\)-metric
- scientific article; zbMATH DE number 1191611 (Why is no real title available?)
- Functional central limit theorems for the Gibbs sampler
- Convergence rates of symmetric scan Gibbs sampler
- Convergence rate of Gibbs sampler and its application
- Rates of convergence for Gibbs sampling in the analysis of almost exchangeable data
- Estimating drift and minorization coefficients for Gibbs sampling algorithms
- Comparison theorems for Gibbs measures
- On rates of convergence of stochastic relaxation for Gaussian and non- Gaussian distributions
This page was built for publication: Convergence rate and concentration inequalities for Gibbs sampling in high dimension
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q470046)
