Error bounds for Approximations of Markov chains used in Bayesian Sampling

We give a number of results on approximations of Markov kernels in total variation and Wasserstein norms weighted by a Lyapunov function. The results are applied to examples from Bayesian statistics where approximations to transition kernels are made to reduce computational costs.

[1]  Richard L. Tweedie,et al.  Markov Chains and Stochastic Stability , 1993, Communications and Control Engineering Series.

[2]  Pierre Alquier,et al.  Noisy Monte Carlo: convergence of Markov chains with approximate transition kernels , 2014, Statistics and Computing.

[3]  Jonathan C. Mattingly,et al.  Coupling and Decoupling to bound an approximating Markov Chain , 2017 .

[4]  H. Haario,et al.  An adaptive Metropolis algorithm , 2001 .

[5]  S. Meyn,et al.  Spectral theory and limit theorems for geometrically ergodic Markov processes , 2002, math/0209200.

[6]  Max Welling,et al.  Austerity in MCMC Land: Cutting the Metropolis-Hastings Budget , 2013, ICML 2014.

[7]  A. Stuart,et al.  Spectral gaps for a Metropolis–Hastings algorithm in infinite dimensions , 2011, 1112.1392.

[8]  N. Pillai,et al.  Ergodicity of Approximate MCMC Chains with Applications to Large Data Sets , 2014, 1405.0182.

[9]  Yee Whye Teh,et al.  Bayesian Learning via Stochastic Gradient Langevin Dynamics , 2011, ICML.

[10]  S. Meyn,et al.  Geometric ergodicity and the spectral gap of non-reversible Markov chains , 2009, 0906.5322.

[11]  Arnaud Doucet,et al.  On Markov chain Monte Carlo methods for tall data , 2015, J. Mach. Learn. Res..

[12]  Jonathan C. Mattingly,et al.  Yet Another Look at Harris’ Ergodic Theorem for Markov Chains , 2008, 0810.2777.

[13]  Sean P. Meyn,et al.  A Liapounov bound for solutions of the Poisson equation , 1996 .

[14]  Jonathan C. Mattingly,et al.  Ergodicity of the 2D Navier-Stokes equations with degenerate stochastic forcing , 2004, math/0406087.

[15]  J. Hobert,et al.  Convergence rates and asymptotic standard errors for Markov chain Monte Carlo algorithms for Bayesian probit regression , 2007 .

[16]  Andrew M. Stuart,et al.  Convergence of Numerical Time-Averaging and Stationary Measures via Poisson Equations , 2009, SIAM J. Numer. Anal..

[17]  R. Tweedie,et al.  Rates of convergence of the Hastings and Metropolis algorithms , 1996 .

[18]  Arnaud Doucet,et al.  Towards scaling up Markov chain Monte Carlo: an adaptive subsampling approach , 2014, ICML.

[19]  Jonathan C. Mattingly,et al.  Asymptotic coupling and a general form of Harris’ theorem with applications to stochastic delay equations , 2009, 0902.4495.

[20]  A. Gelfand,et al.  Gaussian predictive process models for large spatial data sets , 2008, Journal of the Royal Statistical Society. Series B, Statistical methodology.

[21]  S. F. Jarner,et al.  Geometric ergodicity of Metropolis algorithms , 2000 .

[22]  Aaron Smith,et al.  MCMC for Imbalanced Categorical Data , 2016, Journal of the American Statistical Association.

[23]  D. Rudolf,et al.  Perturbation theory for Markov chains via Wasserstein distance , 2015, Bernoulli.

[24]  D. Vere-Jones.  Markov Chains , 1972, Nature.

[25]  A. Y. Mitrophanov,et al.  Sensitivity and convergence of uniformly ergodic Markov chains , 2005 .

[26]  Tianqi Chen,et al.  Stochastic Gradient Hamiltonian Monte Carlo , 2014, ICML.

[27]  J. Rosenthal,et al.  Optimal scaling for various Metropolis-Hastings algorithms , 2001 .