Quantitative contraction rates for Markov chains on general state spaces

DOI10.1214/19-EJP287zbMath1466.60137arXiv1808.07033OpenAlexW2962732064MaRDI QIDQ2631852

Andreas Eberle, Mateusz B. Majka

Publication date: 16 May 2019

Published in: Electronic Journal of Probability (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1808.07033

zbMATH Keywords

Markov chainscouplingsWasserstein distancesEuler schemesmetropolis algorithmquantitative bounds

Mathematics Subject Classification ID

Computational methods in Markov chains (60J22) Monte Carlo methods (65C05) Discrete-time Markov processes on general state spaces (60J05) Numerical analysis or methods applied to Markov chains (65C40) Numerical solutions to stochastic differential and integral equations (65C30)

Related Items (16)

Improved bounds for discretization of Langevin diffusions: near-optimal rates without convexity ⋮ Geometric convergence bounds for Markov chains in Wasserstein distance based on generalized drift and contraction conditions ⋮ Strict Kantorovich contractions for Markov chains and Euler schemes with general noise ⋮ Nonasymptotic bounds for sampling algorithms without log-concavity ⋮ Explicit contraction rates for a class of degenerate and infinite-dimensional diffusions ⋮ Recent advances in the long-time analysis of killed degenerate processes and their particle approximation ⋮ Multi-index antithetic stochastic gradient algorithm ⋮ The forward-backward envelope for sampling with the overdamped Langevin algorithm ⋮ Wasserstein contraction and Poincaré inequalities for elliptic diffusions with high diffusivity ⋮ On the limitations of single-step drift and minorization in Markov chain convergence analysis ⋮ Mixing of Hamiltonian Monte Carlo on strongly log-concave distributions: continuous dynamics ⋮ Approximation of heavy-tailed distributions via stable-driven SDEs ⋮ Efficient stochastic optimisation by unadjusted Langevin Monte Carlo. Application to maximum marginal likelihood and empirical Bayesian estimation ⋮ High-dimensional Bayesian inference via the unadjusted Langevin algorithm ⋮ Maximum Entropy Methods for Texture Synthesis: Theory and Practice ⋮ Mixing time guarantees for unadjusted Hamiltonian Monte Carlo

Cites Work

• \(L^{p}\)-Wasserstein distance for stochastic differential equations driven by Lévy processes
• Reflection couplings and contraction rates for diffusions
• Central limit theorem for Markov processes with spectral gap in the Wasserstein metric
• Spectral gaps for a Metropolis-Hastings algorithm in infinite dimensions
• Subgeometric rates of convergence in Wasserstein distance for Markov chains
• Curvature, concentration and error estimates for Markov chain Monte Carlo
• Reflection coupling and Wasserstein contractivity without convexity
• Asymptotic coupling and a general form of Harris' theorem with applications to stochastic delay equations
• Total variation cutoff in birth-and-death chains
• Mixing and concentration by Ricci curvature
• Separation cut-offs for birth and death chains
• Ricci curvature of Markov chains on metric spaces
• Application of coupling methods to the Neumann eigenvalue problem
• Coupling and exponential ergodicity for stochastic differential equations driven by Lévy processes
• Explicit contraction rates for a class of degenerate and infinite-dimensional diffusions
• Perturbation theory for Markov chains via Wasserstein distance
• Elementary bounds on Poincaré and log-Sobolev constants for decomposable Markov chains
• Estimation of the first eigenvalue of second order elliptic operators
• Refined basic couplings and Wasserstein-type distances for SDEs with Lévy noises
• User-friendly guarantees for the Langevin Monte Carlo with inaccurate gradient
• Transportation inequalities for non-globally dissipative SDEs with jumps via Malliavin calculus and coupling
• Sticky couplings of multidimensional diffusions with different drifts
• High-dimensional Bayesian inference via the unadjusted Langevin algorithm
• Exponential ergodicity for Markov processes with random switching
• Nonasymptotic convergence analysis for the unadjusted Langevin algorithm
• Error bounds for Metropolis-Hastings algorithms applied to perturbations of Gaussian measures in high dimensions
• Subgeometric rates of convergence of Markov processes in the Wasserstein metric
• Spectral gaps in Wasserstein distances and the 2D stochastic Navier-Stokes equations
• Coupling and convergence for Hamiltonian Monte Carlo
• Nonasymptotic bounds for sampling algorithms without log-concavity
• Yet Another Look at Harris’ Ergodic Theorem for Markov Chains
• Transport inequalities, gradient estimates, entropy and Ricci curvature
• Estimation of spectral gap for elliptic operators
• Markov Chains and Stochastic Stability
• Exact solutions to the transportation problem on the line
• Quantitative Harris-type theorems for diffusions and McKean–Vlasov processes
• Analysis and Geometry of Markov Diffusion Operators
• Theoretical Guarantees for Approximate Sampling from Smooth and Log-Concave Densities
• 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: Quantitative contraction rates for Markov chains on general state spaces