Complexity Bounds for MCMC via Diffusion Limits

We connect known results about diusion limits of Markov chain Monte Carlo (MCMC) algorithms to the computer science notion of algorithm complexity. Our main result states that any weak limit of a Markov process implies a corresponding complexity bound (in an appropriate metric). We then combine this result with previously-known MCMC diusion limit results to prove that under appropriate assumptions, the Random-Walk Metropolis (RWM) algorithm in d dimensions takes O(d) iterations to converge to sta- tionarity, while the Metropolis-Adjusted Langevin Algorithm (MALA) takes O(d 1=3 ) iterations to converge to stationarity.

[1]  Stephen A. Cook,et al.  Review: Alan Cobham, Yehoshua Bar-Hillel, The Intrinsic Computational Difficulty of Functions , 1969 .

[2]  Stephen A. Cook,et al.  The complexity of theorem-proving procedures , 1971, STOC.

[3]  C. Givens,et al.  A class of Wasserstein metrics for probability distributions. , 1984 .

[4]  D. Rubin,et al.  Inference from Iterative Simulation Using Multiple Sequences , 1992 .

[5]  J. Rosenthal.  Minorization Conditions and Convergence Rates for Markov Chain Monte Carlo , 1995 .

[6]  J. Rosenthal.  RATES OF CONVERGENCE FOR GIBBS SAMPLING FOR VARIANCE COMPONENT MODELS , 1995 .

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

[8]  A. Gelman,et al.  Weak convergence and optimal scaling of random walk Metropolis algorithms , 1997 .

[9]  J. Rosenthal,et al.  Geometric Ergodicity and Hybrid Markov Chains , 1997 .

[10]  G. Roberts.  Optimal metropolis algorithms for product measures on the vertices of a hypercube , 1998 .

[11]  J. Rosenthal,et al.  Optimal scaling of discrete approximations to Langevin diffusions , 1998 .

[12]  J. Rosenthal.  A First Look at Rigorous Probability Theory , 2000 .

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

[14]  Galin L. Jones,et al.  Honest Exploration of Intractable Probability Distributions via Markov Chain Monte Carlo , 2001 .

[15]  J. Rosenthal.  QUANTITATIVE CONVERGENCE RATES OF MARKOV CHAINS: A SIMPLE ACCOUNT , 2002 .

[16]  J. Rosenthal,et al.  General state space Markov chains and MCMC algorithms , 2004, math/0404033.

[17]  Galin L. Jones,et al.  Sufficient burn-in for Gibbs samplers for a hierarchical random effects model , 2004, math/0406454.

[18]  S. Ethier,et al.  Markov Processes: Characterization and Convergence , 2005 .

[19]  G. Roberts,et al.  OPTIMAL SCALING FOR PARTIALLY UPDATING MCMC ALGORITHMS , 2006, math/0607054.

[20]  M. B'edard.  Weak convergence of Metropolis algorithms for non-i.i.d. target distributions , 2007, 0710.3684.

[21]  M. Bédard.  Optimal acceptance rates for Metropolis algorithms: Moving beyond 0.234 , 2008 .

[22]  G. Roberts,et al.  Optimal Scaling for Random Walk Metropolis on Spherically Constrained Target Densities , 2008 .

[23]  D. Woodard,et al.  Conditions for Rapid and Torpid Mixing of Parallel and Simulated Tempering on Multimodal Distributions , 2009, 0906.2341.

[24]  D. Woodard,et al.  Sufficient Conditions for Torpid Mixing of Parallel and Simulated Tempering , 2009 .

[25]  G. Roberts,et al.  Optimal scaling of the random walk Metropolis on elliptically symmetric unimodal targets , 2009, 0909.0856.

[26]  Andrew Gelman,et al.  Handbook of Markov Chain Monte Carlo , 2011 .

[27]  G. Roberts,et al.  Optimal Scaling of Random Walk Metropolis Algorithms with Non-Gaussian Proposals , 2011 .

[28]  W. K. Yuen,et al.  Optimal scaling of random walk Metropolis algorithms with discontinuous target densities , 2012, 1210.5090.

[29]  B. Jourdain,et al.  Optimal scaling for the transient phase of Metropolis Hastings algorithms: The longtime behavior , 2012, 1212.5517.

[30]  D. Woodard,et al.  Conditions for Torpid Mixing of Parallel and Simulated Tempering on Multimodal Distributions , 2022 .