Convergence rate bounds for iterative random functions using one-shot coupling

DOI10.1007/s11222-022-10134-xzbMath1497.62015arXiv2112.03982OpenAlexW4294276750WikidataQ113900504 ScholiaQ113900504MaRDI QIDQ2080345

Jeffrey S. Rosenthal, Sabrina Sixta

Publication date: 7 October 2022

Published in: Statistics and Computing (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2112.03982

zbMATH Keywords

Markov chainconvergence rateGibbs samplertotal variation distanceiterated random functionsone-shot coupling

Mathematics Subject Classification ID

Computational methods in Markov chains (60J22) Computational methods for problems pertaining to statistics (62-08) Markov chains (discrete-time Markov processes on discrete state spaces) (60J10)

Uses Software

• itsmr

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Convergence rates for a hierarchical Gibbs sampler
• Kac's walk on \(n\)-sphere mixes in \(n\log n\) steps
• Quantitative bounds for Markov chain convergence: Wasserstein and total variation distances
• Faithful couplings of Markov chains: Now equals forever
• Markov chains and stochastic stability
• General state space Markov chains and MCMC algorithms
• On the Markov chain central limit theorem
• Markov chain comparison
• Approximation of product measures with an application to order statistics
• Honest exploration of intractable probability distributions via Markov chain Monte Carlo.
• Locally contractive iterated function systems
• Inference from iterative simulation using multiple sequences
• Stochastic models for time series
• One-shot coupling for certain stochastic recursive sequences.
• Renewal theory and computable convergence rates for geometrically erdgodic Markov chains
• Wasserstein-based methods for convergence complexity analysis of MCMC with applications
• Dimension free convergence rates for Gibbs samplers for Bayesian linear mixed models
• Geometric convergence bounds for Markov chains in Wasserstein distance based on generalized drift and contraction conditions
• Convergence bound in total variation for an image restoration model
• Markov Chains and De-initializing Processes
• Convergence in the Wasserstein Metric for Markov Chain Monte Carlo Algorithms with Applications to Image Restoration
• A First Look at Rigorous Probability Theory
• A First Course in Bayesian Statistical Methods
• A splitting technique for Harris recurrent Markov chains
• Iterated Random Functions
• Covariance structure of the Gibbs sampler with applications to the comparisons of estimators and augmentation schemes
• Introduction to Time Series and Forecasting
• On Choosing and Bounding Probability Metrics
• Minorization Conditions and Convergence Rates for Markov Chain Monte Carlo
• Convergence Rates for Markov Chains
• Linear Algebra and Optimization for Machine Learning
• On the Geometric Ergodicity of Two-Variable Gibbs Samplers
• Quantitative bounds of convergence for geometrically ergodic Markov chain in the Wasserstein distance with application to the Metropolis adjusted Langevin algorithm

This page was built for publication: Convergence rate bounds for iterative random functions using one-shot coupling