On the convergence of adaptive sequential Monte Carlo methods

In several implementations of Sequential Monte Carlo (SMC) methods it is natural and important, in terms of algorithmic efficiency, to exploit the information of the history of the samples to optimally tune their subsequent propagations. In this article we provide a carefully formulated asymptotic theory for a class of such adaptive SMC methods. The theoretical framework developed here will cover, under assumptions, several commonly used SMC algorithms [Chopin, Biometrika 89 (2002) 539-551; Jasra et al., Scand. J. Stat. 38 (2011) 1-22; Schafer and Chopin, Stat. Comput. 23 (2013) 163- 184]. There are only limited results about the theoretical underpinning of such adaptive methods: We will bridge this gap by providing a weak law of large numbers (WLLN) and a central limit theorem (CLT) for some of these algorithms. The latter seems to be the first result of its kind in the literature and provides a formal justification of algorithms used in many real data contexts [Jasra et al. (2011); Schafer and Chopin (2013)]. We establish that for a general class of adaptive SMC algorithms [Chopin (2002)], the asymptotic variance of the estimators from the adaptive SMC method is identical to a "limiting" SMC algorithm which uses ideal proposal kernels. Our results are supported by application on a complex high-dimensional posterior distribution associated with the Navier-Stokes model, where adapting highdimensional parameters of the proposal kernels is critical for the efficiency of the algorithm.

[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]  Arnaud Doucet,et al.  Inference for Lévy‐Driven Stochastic Volatility Models via Adaptive Sequential Monte Carlo , 2011 .

[3]  Pierre Del Moral,et al.  Mean Field Simulation for Monte Carlo Integration , 2013 .

[4]  T. Ferguson.  A Course in Large Sample Theory , 1996 .

[5]  Nicolas Chopin,et al.  Sequential Monte Carlo on large binary sampling spaces , 2011, Statistics and Computing.

[6]  N. Chopin.  Central limit theorem for sequential Monte Carlo methods and its application to Bayesian inference , 2004, math/0508594.

[7]  R. Douc,et al.  Limit theorems for weighted samples with applications to sequential Monte Carlo methods , 2005, math/0507042.

[8]  Arnaud Doucet,et al.  Convergence of Sequential Monte Carlo Methods , 2007 .

[9]  Arnaud Debussche,et al.  Stochastic partial differential equations: analysis and computations , 2013, Stochastic Partial Differential Equations: Analysis and Computations.

[10]  A. Doucet,et al.  A Tutorial on Particle Filtering and Smoothing: Fifteen years later , 2008 .

[11]  F. Cérou,et al.  Fluctuation Analysis of Adaptive Multilevel Splitting , 2014, 1408.6366.

[12]  P. Moral,et al.  A non asymptotic variance theorem for unnormalized Feynman-Kac particle models , 2008 .

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

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

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

[16]  C. Doering,et al.  Applied analysis of the Navier-Stokes equations: Index , 1995 .

[17]  N. Whiteley.  Stability properties of some particle filters , 2011, 1109.6779.

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

[19]  Xiao-Li Meng,et al.  Simulating Normalizing Constants: From Importance Sampling to Bridge Sampling to Path Sampling , 1998 .

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

[21]  Gareth Roberts,et al.  Optimal scalings for local Metropolis--Hastings chains on nonproduct targets in high dimensions , 2009, 0908.0865.

[22]  T. Lai,et al.  A general theory of particle filters in hidden Markov models and some applications , 2013, 1312.5114.

[23]  C. Andrieu,et al.  On the ergodicity properties of some adaptive MCMC algorithms , 2006, math/0610317.

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

[25]  G. Roberts,et al.  MCMC Methods for Functions: ModifyingOld Algorithms to Make Them Faster , 2012, 1202.0709.

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

[27]  R. Douc,et al.  Long-term stability of sequential Monte Carlo methods under verifiable conditions , 2012, 1203.6898.