Quantitative bounds for Markov chain convergence: Wasserstein and total variation distances

DOI10.3150/09-BEJ238zbMath1284.60143arXiv1102.5245WikidataQ29030176 ScholiaQ29030176MaRDI QIDQ637086

Neal Madras, A. Deniz Sezer

Publication date: 2 September 2011

Published in: Bernoulli (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1102.5245

zbMATH Keywords

Markov chainconvergence ratelogistic mapGibbs samplercouplingrandom dynamical systemWasserstein distancetotal variation distancelocal contractivityiterated random functions

Mathematics Subject Classification ID

Computational methods in Markov chains (60J22) Discrete-time Markov processes on general state spaces (60J05) Dynamical systems and their relations with probability theory and stochastic processes (37A50)

Related Items

Limit behavior of the invariant measure for Langevin dynamics ⋮ Dimension free convergence rates for Gibbs samplers for Bayesian linear mixed models ⋮ A computational procedure for estimation of the mixing time of the random-scan Metropolis algorithm ⋮ Optimal transportation and stationary measures for iterated function systems ⋮ Convergence rates of the blocked Gibbs sampler with random scan in the Wasserstein metric ⋮ Qualitative Robustness in Bayesian Inference ⋮ Geometric ergodicity of a hybrid sampler for Bayesian inference of phylogenetic branch lengths ⋮ Spectral telescope: convergence rate bounds for random-scan Gibbs samplers based on a hierarchical structure ⋮ Exact convergence analysis for metropolis–hastings independence samplers in Wasserstein distances ⋮ Perturbation theory for Markov chains via Wasserstein distance ⋮ Convergence bound in total variation for an image restoration model ⋮ Geometric ergodicity of a Metropolis-Hastings algorithm for Bayesian inference of phylogenetic branch lengths ⋮ High-dimensional MCMC with a standard splitting scheme for the underdamped Langevin diffusion ⋮ On the limitations of single-step drift and minorization in Markov chain convergence analysis ⋮ Ergodicity of Markov Processes via Nonstandard Analysis ⋮ Lack of phase transitions in staggered magnetic systems. A comparison of uniqueness criteria ⋮ Convergence rates of symmetric scan Gibbs sampler ⋮ Computable upper bounds on the distance to stationarity for Jovanovski and Madras's Gibbs sampler ⋮ On the convergence complexity of Gibbs samplers for a family of simple Bayesian random effects models ⋮ Convergence rate bounds for iterative random functions using one-shot coupling ⋮ Mixing time guarantees for unadjusted Hamiltonian Monte Carlo ⋮ Stochastic Gradient MCMC for State Space Models ⋮ Wasserstein-based methods for convergence complexity analysis of MCMC with applications

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Markov chains and stochastic stability
• Explicit stationary distributions for compositions of random functions and products of random matrices
• General state space Markov chains and MCMC algorithms
• Geometric ergodicity of Gibbs and block Gibbs samplers for a hierarchical random effects model
• Geometric ergodicity and hybrid Markov chains
• Honest exploration of intractable probability distributions via Markov chain Monte Carlo.
• Locally contractive iterated function systems
• One-shot coupling for certain stochastic recursive sequences.
• Random logistic maps and Lyapunov exponents
• One-shot CFTP; application to a class of truncated Gaussian densities
• Convergence in the Wasserstein Metric for Markov Chain Monte Carlo Algorithms with Applications to Image Restoration
• A new class of markov processes for image encoding
• Iterated Random Functions
• On Choosing and Bounding Probability Metrics
• Topics in the Constructive Theory of Countable Markov Chains
• Minorization Conditions and Convergence Rates for Markov Chain Monte Carlo
• Perfect Simulation for Image Restoration
• Lectures on Monte Carlo methods