Error Bounds and Normalising Constants for Sequential Monte Carlo Samplers in High Dimensions

In this paper we develop a collection of results associated to the analysis of the sequential Monte Carlo (SMC) samplers algorithm, in the context of high-dimensional independent and identically distributed target probabilities. The SMC samplers algorithm can be designed to sample from a single probability distribution, using Monte Carlo to approximate expectations with respect to this law. Given a target density in d dimensions our results are concerned with d → ∞, while the number of Monte Carlo samples, N, remains fixed. We deduce an explicit bound on the Monte-Carlo error for estimates derived using the SMC sampler and the exact asymptotic relative -error of the estimate of the normalising constant associated to the target. We also establish marginal propagation of chaos properties of the algorithm. These results are deduced when the cost of the algorithm is O(Nd 2).

[1]  Alexandros Beskos,et al.  Sequential Monte Carlo Methods for High-Dimensional Inverse Problems: A Case Study for the Navier-Stokes Equations , 2013, SIAM/ASA J. Uncertain. Quantification.

[2]  R. Handel,et al.  Can local particle filters beat the curse of dimensionality , 2013, 1301.6585.

[3]  D. Nott,et al.  The ensemble Kalman filter is an ABC algorithm , 2012, Stat. Comput..

[4]  Arnaud Doucet,et al.  An adaptive sequential Monte Carlo method for approximate Bayesian computation , 2011, Statistics and Computing.

[5]  Nikolaus Schweizer.  Non-asymptotic Error Bounds for Sequential MCMC and Stability of Feynman-Kac Propagators , 2012, 1204.2382.

[6]  P. Moral,et al.  On adaptive resampling strategies for sequential Monte Carlo methods , 2012, 1203.0464.

[7]  D. S. McCormick,et al.  Stability of Filters for the Navier-Stokes Equation , 2011, 1110.2527.

[8]  N. Kantas,et al.  Linear Variance Bounds for Particle Approximations of Time-Homogeneous Feynman-Kac Formulae , 2011, 1108.3988.

[9]  N. Pillai,et al.  On the random walk metropolis algorithm for Gaussian random field priors and the gradient flow , 2011 .

[10]  P. Moral,et al.  A nonasymptotic theorem for unnormalized Feynman-Kac particle models , 2011 .

[11]  A. Beskos,et al.  On the stability of sequential Monte Carlo methods in high dimensions , 2011, 1103.3965.

[12]  N. Whiteley.  Sequential Monte Carlo Samplers: Error Bounds and Insensitivity to Initial Conditions , 2011, 1103.3970.

[13]  Sumeetpal S. Singh,et al.  Particle approximations of the score and observed information matrix in state space models with application to parameter estimation , 2011 .

[14]  A. Eberle,et al.  Quantitative approximations of evolving probability measures and sequential Markov chain Monte Carlo methods , 2010, Probability Theory and Related Fields.

[15]  Christian Musso,et al.  An insight into the issue of dimensionality in particle filtering , 2010, 2010 13th International Conference on Information Fusion.

[16]  Sumeetpal S. Singh,et al.  Filtering via approximate Bayesian computation , 2010, Statistics and Computing.

[17]  Elise Arnaud,et al.  SMC with adaptive resampling: Large sample asymptotics , 2009, 2009 IEEE/SP 15th Workshop on Statistical Signal Processing.

[18]  R. Handel.  Uniform time average consistency of Monte Carlo particle filters , 2008, 0812.0350.

[19]  P. Bickel,et al.  Obstacles to High-Dimensional Particle Filtering , 2008 .

[20]  P. Bickel,et al.  Sharp failure rates for the bootstrap particle filter in high dimensions , 2008, 0805.3287.

[21]  P. Bickel,et al.  Curse-of-dimensionality revisited: Collapse of the particle filter in very large scale systems , 2008, 0805.3034.

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

[23]  S. Meyn,et al.  Large Deviations Asymptotics and the Spectral Theory of Multiplicatively Regular Markov Processes , 2005, math/0509310.

[24]  L. A. Breyer,et al.  Optimal scaling of MaLa for nonlinear regression , 2004, math/0407132.

[25]  Refik Soyer,et al.  Bayesian Methods for Nonlinear Classification and Regression , 2004, Technometrics.

[26]  P. Moral.  Feynman-Kac Formulae: Genealogical and Interacting Particle Systems with Applications , 2004 .

[27]  P. Moral,et al.  Sequential Monte Carlo samplers , 2002, cond-mat/0212648.

[28]  N. Chopin.  A sequential particle filter method for static models , 2002 .

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

[30]  Simon J. Godsill,et al.  Improvement Strategies for Monte Carlo Particle Filters , 2001, Sequential Monte Carlo Methods in Practice.

[31]  Simon J. Godsill,et al.  On sequential Monte Carlo sampling methods for Bayesian filtering , 2000, Stat. Comput..

[32]  Radford M. Neal.  Annealed importance sampling , 1998, Stat. Comput..

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

[34]  C. Jarzynski.  Nonequilibrium Equality for Free Energy Differences , 1996, cond-mat/9610209.

[35]  François Le Gland,et al.  Particle and cell approximations for nonlinear filtering , 1995 .

[36]  F. Gland,et al.  Large sample asymptotics for the ensemble Kalman filter , 2009 .

[37]  P. Moral,et al.  Sequential Monte Carlo samplers for rare events , 2006 .

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