Asymptotically Optimal Discrete-Time Nonlinear Filters From Stochastically Convergent State Process Approximations

We consider the problem of approximating optimal in the Minimum Mean Squared Error (MMSE) sense nonlinear filters in a discrete time setting, exploiting properties of stochastically convergent state process approximations. More specifically, we consider a class of nonlinear, partially observable stochastic systems, comprised by a (possibly nonstationary) hidden stochastic process (the state), observed through another conditionally Gaussian stochastic process (the observations). Under general assumptions, we show that, given an approximating process which, for each time step, is stochastically convergent to the state process, an approximate filtering operator can be defined, which converges to the true optimal nonlinear filter of the state in a strong and well defined sense. In particular, the convergence is compact in time and uniform in a completely characterized set of probability measure almost unity. The results presented in this paper can form a common basis for the analysis and characterization of a number of popular but heuristic approaches for approximating optimal nonlinear filters, such as approximate grid based techniques.

[1]  G. Pagès,et al.  Optimal quantization methods for nonlinear filtering with discrete-time observations , 2005 .

[2]  S. Eddy Hidden Markov models. , 1996, Current opinion in structural biology.

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

[4]  Neil J. Gordon,et al.  A tutorial on particle filters for online nonlinear/non-Gaussian Bayesian tracking , 2002, IEEE Trans. Signal Process..

[5]  Athina P. Petropulu,et al.  Mobi-cliques for improving ergodic secrecy in fading wiretap channels under power constraints , 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[6]  Aarnout Brombacher,et al.  Probability... , 2009, Qual. Reliab. Eng. Int..

[7]  Athina P. Petropulu,et al.  Controlling groups of mobile beamformers , 2012, 2012 IEEE 51st IEEE Conference on Decision and Control (CDC).

[8]  A. M. Mathai,et al.  Quadratic forms in random variables : theory and applications , 1992 .

[9]  H. Kushner Numerical Methods for Stochastic Control Problems in Continuous Time , 2000 .

[10]  I. Miller Probability, Random Variables, and Stochastic Processes , 1966 .

[11]  C. L. Nikias,et al.  Higher-order spectra analysis : a nonlinear signal processing framework , 1993 .

[12]  L. Pratelli,et al.  Almost sure weak convergence of random probability measures , 2006 .

[13]  Steven I. Marcus,et al.  Optimal nonlinear estimation for a class of discrete-time stochastic systems , 1979 .

[14]  R. Bass,et al.  Review: P. Billingsley, Convergence of probability measures , 1971 .

[15]  N. Yoshida CENTRAL LIMIT THEOREM FOR BRANCHING RANDOM WALKS , 2008 .

[16]  Adrian Segall,et al.  Stochastic processes in estimation theory , 1976, IEEE Trans. Inf. Theory.

[17]  R. Ash,et al.  Probability and measure theory , 1999 .

[18]  Bruno O. Shubert,et al.  Random variables and stochastic processes , 1979 .

[19]  Kristine L. Bell,et al.  A Tutorial on Particle Filters for Online Nonlinear/NonGaussian Bayesian Tracking , 2007 .

[20]  Robert J. Elliott,et al.  New finite-dimensional filters for parameter estimation of discrete-time linear Gaussian models , 1999, IEEE Trans. Autom. Control..

[21]  Athina P. Petropulu,et al.  Sequential Channel State Tracking & SpatioTemporal Channel Prediction in Mobile Wireless Sensor Networks , 2015, ArXiv.

[22]  F. Daum Nonlinear filters: beyond the Kalman filter , 2005, IEEE Aerospace and Electronic Systems Magazine.

[23]  Kazufumi Ito,et al.  Gaussian filters for nonlinear filtering problems , 2000, IEEE Trans. Autom. Control..

[24]  John G. Proakis,et al.  Probability, random variables and stochastic processes , 1985, IEEE Trans. Acoust. Speech Signal Process..

[25]  Adrian Segall,et al.  Recursive estimation from discrete-time point processes , 1976, IEEE Trans. Inf. Theory.

[26]  Leonard F. Richardson,et al.  Measure and Integration: A Concise Introduction to Real Analysis , 2009 .

[27]  Robert J. Elliott,et al.  Exact adaptive filters for Markov chains observed in Gaussian noise , 1994, Autom..

[28]  H. Kushner Approximations to optimal nonlinear filters , 1967, IEEE Transactions on Automatic Control.

[29]  Athina P. Petropulu,et al.  Mobile jammers for secrecy rate maximization in cooperative networks , 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

[30]  P. Massart,et al.  Adaptive estimation of a quadratic functional by model selection , 2000 .

[31]  Robert J. Elliott,et al.  How to count and guess well: Discrete adaptive filters , 1994 .

[32]  Harold J. Kushner,et al.  Numerical Approximations to Optimal Nonlinear Filters , 2008 .

[33]  Zakhar Kabluchko,et al.  A functional central limit theorem for branching random walks, almost sure weak convergence, and applications to random trees , 2014 .