Spectral telescope: convergence rate bounds for random-scan Gibbs samplers based on a hierarchical structure

DOI10.1214/23-aap1992arXiv2208.11299OpenAlexW4391483051MaRDI QIDQ6126804

Qian Qin, Guanyang Wang

Publication date: 10 April 2024

Published in: The Annals of Applied Probability (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2208.11299

zbMATH Keywords

spectral gapGlauber dynamicsmixing timerecursive algorithminfluence matrixspectral independence

Mathematics Subject Classification ID

Sums of independent random variables; random walks (60G50) Probability distributions: general theory (60E05)

Cites Work

• Unnamed Item
• Unnamed Item
• Convergence rate and concentration inequalities for Gibbs sampling in high dimension
• Geometric ergodicity of random scan Gibbs samplers for hierarchical one-way random effects models
• Kac's walk on \(n\)-sphere mixes in \(n\log n\) steps
• Quantitative bounds for Markov chain convergence: Wasserstein and total variation distances
• Asymptotic coupling and a general form of Harris' theorem with applications to stochastic delay equations
• Gibbs sampling, exponential families and orthogonal polynomials
• A covariance estimate for Gibbs measures
• Geometric ergodicity and hybrid Markov chains
• On the mixing time of Kac's walk and other high-dimensional Gibbs samplers with constraints
• One-shot coupling for certain stochastic recursive sequences.
• Spectral gap for Kac's model of Boltzmann equation.
• Determination of the spectral gap for Kac's master equation and related stochastic evolution.
• Wasserstein-based methods for convergence complexity analysis of MCMC with applications
• Geometric convergence bounds for Markov chains in Wasserstein distance based on generalized drift and contraction conditions
• Mixing time of an unaligned Gibbs sampler on the square
• Concentration of measure without independence: a unified approach via the martingale method
• A Gibbs sampler on the \(n\)-simplex
• Subgeometric rates of convergence of Markov processes in the Wasserstein metric
• On the spectra of sums of orthogonal projections with applications to parallel computing
• Markov Chains
• Spectral Independence in High-Dimensional Expanders and Applications to the Hardcore Model
• Improved analysis of higher order random walks and applications
• Prescribing a System of Random Variables by Conditional Distributions
• Rates of convergence for Gibbs sampling in the analysis of almost exchangeable data

This page was built for publication: Spectral telescope: convergence rate bounds for random-scan Gibbs samplers based on a hierarchical structure