Perturbation theory for Markov chains via Wasserstein distance

DOI10.3150/17-BEJ938zbMath1465.60065arXiv1503.04123OpenAlexW2964282829MaRDI QIDQ1708977

Nikolaus Schweizer, Daniel Rudolf

Publication date: 27 March 2018

Published in: Bernoulli (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1503.04123

zbMATH Keywords

Markov chainsperturbationsWasserstein distanceMCMCbig data

Mathematics Subject Classification ID

Computational methods in Markov chains (60J22) Discrete-time Markov processes on general state spaces (60J05) Convergence of probability measures (60B10)

Related Items (40)

Quantitative contraction rates for Markov chains on general state spaces ⋮ Connecting the Dots: Numerical Randomized Hamiltonian Monte Carlo with State-Dependent Event Rates ⋮ Strict Kantorovich contractions for Markov chains and Euler schemes with general noise ⋮ Stability of noisy Metropolis-Hastings ⋮ Challenges in Markov chain Monte Carlo for Bayesian neural networks ⋮ Unnamed Item ⋮ Nonasymptotic bounds for sampling algorithms without log-concavity ⋮ Rate-optimal refinement strategies for local approximation MCMC ⋮ Bayesian Imaging with Data-Driven Priors Encoded by Neural Networks ⋮ Explicit contraction rates for a class of degenerate and infinite-dimensional diffusions ⋮ Spectral gaps and error estimates for infinite-dimensional Metropolis-Hastings with non-Gaussian priors ⋮ Bayesian Inverse Problems Are Usually Well-Posed ⋮ An Integrated Transportation Distance between Kernels and Approximate Dynamic Risk Evaluation in Markov Systems ⋮ Wasserstein perturbations of Markovian transition semigroups ⋮ Robustness of iterated function systems of Lipschitz maps ⋮ Explicit bounds for spectral theory of geometrically ergodic Markov kernels and applications ⋮ Stability of doubly-intractable distributions ⋮ A perturbation analysis of Markov chains models with time-varying parameters ⋮ Mean field Markov decision processes ⋮ On the Study of Forward Kolmogorov System and the Corresponding Problems for Inhomogeneous Continuous-Time Markov Chains ⋮ State-discretization of \(V\)-geometrically ergodic Markov chains and convergence to the stationary distribution ⋮ Quantitative Harris-type theorems for diffusions and McKean–Vlasov processes ⋮ Posterior asymptotics in Wasserstein metrics on the real line ⋮ Using Coupling Methods to Estimate Sample Quality of Stochastic Differential Equations ⋮ Perturbation bounds for Monte Carlo within metropolis via restricted approximations ⋮ Quantitative spectral gap estimate and Wasserstein contraction of simple slice sampling ⋮ Lack of phase transitions in staggered magnetic systems. A comparison of uniqueness criteria ⋮ Wasserstein upper bounds of the total variation for smooth densities ⋮ On limiting characteristics for a non-stationary two-processor heterogeneous system ⋮ On three methods for bounding the rate of convergence for some continuous-time Markov chains ⋮ Empirical optimal transport on countable metric spaces: distributional limits and statistical applications ⋮ Bayesian computation: a summary of the current state, and samples backwards and forwards ⋮ On the Well-posedness of Bayesian Inverse Problems ⋮ Uncertainty Quantification for Markov Processes via Variational Principles and Functional Inequalities ⋮ Unnamed Item ⋮ Error bounds of the invariant statistics in machine learning of ergodic Itô diffusions ⋮ Informed sub-sampling MCMC: approximate Bayesian inference for large datasets ⋮ On the local Lipschitz stability of Bayesian inverse problems ⋮ Approximations of geometrically ergodic reversible markov chains ⋮ Stochastic Gradient MCMC for State Space Models

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Stability of noisy Metropolis-Hastings
• Spectral gaps for a Metropolis-Hastings algorithm in infinite dimensions
• Quantitative bounds for Markov chain convergence: Wasserstein and total variation distances
• Approximate Bayesian computational methods
• General state space Markov chains and MCMC algorithms
• Ricci curvature of Markov chains on metric spaces
• A note on Metropolis-Hastings kernels for general state spaces
• Exponential convergence of Langevin distributions and their discrete approximations
• Geometric ergodicity and hybrid Markov chains
• Renewal theory and computable convergence rates for geometrically erdgodic Markov chains
• Rates of convergence of the Hastings and Metropolis algorithms
• Error bounds for Metropolis-Hastings algorithms applied to perturbations of Gaussian measures in high dimensions
• Noisy Monte Carlo: convergence of Markov chains with approximate transition kernels
• Explicit error bounds for Markov chain Monte Carlo
• Yet Another Look at Harris’ Ergodic Theorem for Markov Chains
• Maximal coupling procedure and stability of discrete Markov chains. I
• Convergence in the Wasserstein Metric for Markov Chain Monte Carlo Algorithms with Applications to Image Restoration
• Markov Chains and Stochastic Stability
• Inequalities in Theorems of Ergodicity and Stability for Markov Chains with Common Phase Space. I
• Convergence Properties of Perturbed Markov Chains
• A Perturbation Theory for Ergodic Markov Chains and Application to Numerical Approximations
• Numerical integration using V-uniformly ergodic Markov chains
• Stability and exponential convergence of continuous-time Markov chains
• Regular Perturbation of V-Geometrically Ergodic Markov Chains
• Sensitivity and convergence of uniformly ergodic Markov chains
• Optimal Transport
• A note on geometric ergodicity and floating-point roundoff error
• 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: Perturbation theory for Markov chains via Wasserstein distance