Coupling from the past with randomized quasi-Monte Carlo

The coupling-from-the-past (CFTP) algorithm of Propp and Wilson permits one to sample exactly from the stationary distribution of an ergodic Markov chain. By using it n times independently, we obtain an independent sample from that distribution. A more representative sample can be obtained by creating negative dependence between these n replicates; other authors have already proposed to do this via antithetic variates, Latin hypercube sampling, and randomized quasi-Monte Carlo (RQMC). We study a new, often more effective, way of combining CFTP with RQMC, based on the array-RQMC algorithm. We provide numerical illustrations for Markov chains with both finite and continuous state spaces, and compare with the RQMC combinations proposed earlier.

[1]  Peter W. Glynn,et al.  Chapter 16 Simulation Algorithms for Regenerative Processes , 2006, Simulation.

[2]  Pierre L'Ecuyer,et al.  Quasi-Monte Carlo Simulation of Discrete-Time Markov Chains on Multidimensional State Spaces , 2006 .

[3]  Brian D. Ripley,et al.  Stochastic Simulation , 2005 .

[4]  Pierre L'Ecuyer,et al.  Uniform random number generation , 1994, Ann. Oper. Res..

[5]  Christian P. Robert,et al.  Monte Carlo Statistical Methods , 2005, Springer Texts in Statistics.

[6]  Finkel,et al.  Brief review: Stochastic Modeling and the Theory of Queues by Ronald W. Wolfe (Prentice-Hall, 1989) , 1992, PERV.

[7]  Xiao-Li Meng,et al.  Antithetic Coupling for Perfect Sampling , 2000 .

[8]  P. L’Ecuyer,et al.  Variance Reduction via Lattice Rules , 1999 .

[9]  N. J. A. Sloane,et al.  Sphere Packings, Lattices and Groups , 1987, Grundlehren der mathematischen Wissenschaften.

[10]  Harald Niederreiter,et al.  Random number generation and Quasi-Monte Carlo methods , 1992, CBMS-NSF regional conference series in applied mathematics.

[11]  P. L’Ecuyer,et al.  On Array-RQMC for Markov Chains: Mapping Alternatives and Convergence Rates , 2008 .

[12]  Steven A. Orszag,et al.  CBMS-NSF REGIONAL CONFERENCE SERIES IN APPLIED MATHEMATICS , 1978 .

[13]  Radu V. Craiu,et al.  Multiprocess parallel antithetic coupling for backward and forward Markov Chain Monte Carlo , 2005, math/0505631.

[14]  George S. Fishman,et al.  Discrete-Event Simulation : Modeling, Programming, and Analysis , 2001 .

[15]  Pierre L'Ecuyer,et al.  Quasi-Monte Carlo methods with applications in finance , 2008, Finance Stochastics.

[16]  George S. Fishman,et al.  Discrete-event simulation , 2001 .

[17]  Pierre L'Ecuyer,et al.  Chapter 3 Uniform Random Number Generation , 2006, Simulation.

[18]  Pierre L'Ecuyer,et al.  A Randomized Quasi-Monte Carlo Simulation Method for Markov Chains , 2006, Oper. Res..

[19]  Christian P. Robert,et al.  Monte Carlo Statistical Methods (Springer Texts in Statistics) , 2005 .

[20]  Peter W. Glynn,et al.  On the theoretical comparison of low-bias steady-state estimators , 2007, TOMC.

[21]  I. Sloan.  Lattice Methods for Multiple Integration , 1994 .

[22]  Pierre L'Ecuyer,et al.  Recent Advances in Randomized Quasi-Monte Carlo Methods , 2002 .

[23]  Philip Heidelberger,et al.  Simulation Run Length Control in the Presence of an Initial Transient , 1983, Oper. Res..

[24]  George L. Nemhauser,et al.  Handbooks in operations research and management science , 1989 .

[25]  Ronald W. Wolff,et al.  Stochastic Modeling and the Theory of Queues , 1989 .

[26]  Averill M. Law,et al.  Simulation Modeling and Analysis , 1982 .

[27]  Art B. Owen,et al.  Variance with alternative scramblings of digital nets , 2003, TOMC.

[28]  Christiane Lemieux,et al.  Exact sampling with highly uniform point sets , 2006, Math. Comput. Model..

[29]  Art B. Owen,et al.  Latin supercube sampling for very high-dimensional simulations , 1998, TOMC.

[30]  David Bruce Wilson,et al.  Exact sampling with coupled Markov chains and applications to statistical mechanics , 1996, Random Struct. Algorithms.