Curvature, concentration and error estimates for Markov chain Monte Carlo

DOI10.1214/10-AOP541zbMath1207.65006arXiv0904.1312MaRDI QIDQ606638

Publication date: 18 November 2010

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

Full work available at URL: https://arxiv.org/abs/0904.1312

zbMATH Keywords

convergence; Markov chain Monte Carlo method; Ricci curvature; Ising model; concentration of measure; Wasserstein distance; \(M/M/\infty\) queueing process; Euler scheme for diffusions; explicit nonasymptotic

Mathematics Subject Classification ID

60J22: Computational methods in Markov chains

65C05: Monte Carlo methods

60K25: Queueing theory (aspects of probability theory)

65C40: Numerical analysis or methods applied to Markov chains

60J60: Diffusion processes

62E17: Approximations to statistical distributions (nonasymptotic)

65C30: Numerical solutions to stochastic differential and integral equations

82C44: Dynamics of disordered systems (random Ising systems, etc.) in time-dependent statistical mechanics

Related Items

Quantitative Harris-type theorems for diffusions and McKean–Vlasov processes, Empirical measures: regularity is a counter-curse to dimensionality, Multilevel Monte Carlo Estimation of the Expected Value of Sample Information, Forward sensitivity analysis for contracting stochastic systems, Computation of Expectations by Markov Chain Monte Carlo Methods, Exponential inequalities for unbounded functions of geometrically ergodic Markov chains: applications to quantitative error bounds for regenerative Metropolis algorithms, Information geometry approach to parameter estimation in Markov chains, Reflection couplings and contraction rates for diffusions, Exact and asymptotic results on coarse Ricci curvature of graphs, Convergence rate and concentration inequalities for Gibbs sampling in high dimension, Spectral gaps for a Metropolis-Hastings algorithm in infinite dimensions, The mathematics of mixing things up, Sampling the Fermi statistics and other conditional product measures, Mixing and concentration by Ricci curvature, Rapid mixing of geodesic walks on manifolds with positive curvature, Ricci-Ollivier curvature of the rooted phylogenetic subtree-prune-regraft graph, Explicit contraction rates for a class of degenerate and infinite-dimensional diffusions, Using perturbed underdamped Langevin dynamics to efficiently sample from probability distributions, Normalizing constants of log-concave densities, Exponential inequalities for nonstationary Markov chains, On a Metropolis-Hastings importance sampling estimator, Lower bound for the coarse Ricci curvature of continuous-time pure-jump processes, Function-specific mixing times and concentration away from equilibrium, Non-asymptotic Gaussian estimates for the recursive approximation of the invariant distribution of a diffusion, Convergence rates of symmetric scan Gibbs sampler, Measuring sample quality with diffusions, A weighted discrepancy bound of quasi-Monte Carlo importance sampling, High-dimensional Bayesian inference via the unadjusted Langevin algorithm, Rademacher complexity for Markov chains: applications to kernel smoothing and Metropolis-Hastings, Error bounds of MCMC for functions with unbounded stationary variance, On efficient randomized algorithms for finding the PageRank vector, Nonasymptotic bounds on the estimation error of MCMC algorithms, On the mean speed of convergence of empirical and occupation measures in Wasserstein distance, Quantitative contraction rates for Markov chains on general state spaces, Coupling and convergence for Hamiltonian Monte Carlo, Transport-information inequalities for Markov chains, Nonasymptotic bounds for sampling algorithms without log-concavity, Online Discrete Optimization in Social Networks in the Presence of Knightian Uncertainty, Hit-and-Run for Numerical Integration

Cites Work