Abstract

Particle filters (PFs), which are successful methods for approximating the solution of the filtering problem, can be divided into two types: weighted and unweighted PFs. It is well known that weighted PFs suffer from the weight degeneracy and curse of dimensionality. To sidestep these issues, unweighted PFs have been gaining attention, though they have their own challenges. The existing literature on these types of PFs is based on distinct approaches. In order to establish a connection, we put forward a framework that unifies weighted and unweighted PFs in the continuous-time filtering problem. We show that the stochastic dynamics of a particle system described by a pair process, representing particles and their importance weights, should satisfy two necessary conditions in order for its distribution to match the solution of the Kushner--Stratonovich equation. In particular, we demonstrate that the bootstrap particle filter (BPF), which relies on importance sampling, and the feedback particle filter (FPF), which is an unweighted PF based on optimal control, arise as special cases from a broad class and that there is a smooth transition between the two. The freedom in designing the PF dynamics opens up potential ways to address the existing issues in the aforementioned algorithms, namely weight degeneracy in the BPF and gain estimation in the FPF.

Keywords

  1. nonlinear filtering
  2. Kushner--Stratonovich equation
  3. Fokker--Planck equation
  4. stochastic differential equations
  5. McKean--Vlasov processes
  6. interacting particle systems
  7. importance sampling

MSC codes

  1. 60G35
  2. 60H15
  3. 65C35
  4. 65C05
  5. 35Q84

Formats available

You can view the full content in the following formats:

References

1.
E. Abedi and S. C. Surace, Gauge freedom within the class of linear feedback particle filters, in Proceedings of the 58th IEEE Conference on Decision and Control (CDC), 2019, pp. 666--671, https://doi.org/10.1109/CDC40024.2019.9029897.
2.
A. Bain and D. Crisan, Fundamentals of Stochastic Filtering, Springer-Verlag, New York, 2009, https://doi.org/10.1007/978-0-387-76896-0.
3.
P. K. Bhattacharya, Estimation of a probability density function and its derivatives, Sankhyā Ser. A, 29 (1967), pp. 373--382.
4.
W. Cao, A. Dytso, M. Fauß, H. V. Poor, and G. Feng, Nonparametric Estimation of the Fisher Information and Its Applications, preprint, https://arxiv.org/abs/2005.03622, 2020.
5.
N. Chopin, Central limit theorem for sequential Monte Carlo methods and its application to Bayesian inference, Ann. Statist., 32 (2004), pp. 2385--2411, https://doi.org/10.1214/009053604000000698.
6.
A. Doucet, S. Godsill, and C. Andrieu, On sequential Monte Carlo sampling methods for Bayesian filtering, Stat. Comput., 10 (2000), pp. 197--208.
7.
A. Doucet and A. Johansen, A tutorial on particle filtering and smoothing: Fifteen years later, in The Oxford Handbook of Nonlinear Filtering, Oxford University Press, Oxford, UK, 2011, pp. 656--704.
8.
V. Fabian, Estimation of the derivative of the logarithm of a density, Ann. Statist., 1 (1973), pp. 557--561, https://doi.org/10.1214/aos/1176342424.
9.
I. M. Gelfand and S. V. Fomin, Calculus of Variations, Prentice-Hall, Englewood Cliffs, NJ, 1963.
10.
N. J. Gordon, D. J. Salmond, and A. F. M. Smith, Novel approach to nonlinear/non-Gaussian Bayesian state estimation, IEEE Proc.-F, 140 (1993), pp. 107--113, https://doi.org/10.1049/ip-f-2.1993.0015.
11.
R. E. Kalman and R. S. Bucy, New results in linear filtering and prediction theory, J. Basic Eng., 83 (1961), pp. 95--108, https://doi.org/10.1115/1.3658902.
12.
F. C. Klebaner, Introduction to Stochastic Calculus With Applications, 2nd ed., Imperial College Press, London, 2005, https://doi.org/10.1142/P386.
13.
H. Kunita, Some extensions of Ito's formula, in Seminar of Probability, XV, University of Strasbourg, Strasbourg, France, 1981, pp. 118--141, http://www.numdam.org/item/SPS_1981__15__118_0.
14.
H. J. Kushner, On the differential equations satisfied by conditional probability densities of Markov processes, with applications, J. SIAM Control Ser. A, 2 (1964), pp. 106--119, https://doi.org/10.1137/0302009.
15.
A. Kutschireiter, S. C. Surace, and J.-P. Pfister, The Hitchhiker's guide to nonlinear filtering, J. Math. Psychol., 94 (2020), 102307, https://doi.org/10.1016/j.jmp.2019.102307.
16.
J. Lott, Some geometric calculations on Wasserstein space, Comm. Math. Phys., 277 (2008), pp. 423--437, https://doi.org/10.1007/s00220-007-0367-3.
17.
L. Martino, V. Elvira, and F. Louzada, Effective sample size for importance sampling based on discrepancy measures, Signal Process., 131 (2017), pp. 386--401, https://doi.org/10.1016/j.sigpro.2016.08.025.
18.
S. Pathiraja, S. Reich, and W. Stannat, McKean--Vlasov SDEs in nonlinear filtering, SIAM J. Control Optim., 59 (2021), pp. 4188--4215, https://doi.org/10.1137/20M1355197.
19.
A. Radhakrishnan and S. Meyn, Feedback particle filter design using a differential-loss reproducing kernel Hilbert space, in Proceedings of the Annual American Control Conference (ACC), 2018, pp. 329--336, https://doi.org/10.23919/ACC.2018.8431689.
20.
S. Reich, Data assimilation: The Schrödinger perspective, Acta Numer., 28 (2019), pp. 635--711, https://doi.org/10.1017/S0962492919000011.
21.
S. Särkká and A. Solin, Applied Stochastic Differential Equations, IMS Textb. 10, Cambridge University Press, Cambridge, UK, 2019.
22.
E. F. Schuster, Estimation of a probability density function and its derivatives, Ann. Math. Statist., 40 (1969), pp. 1187--1195, https://doi.org/10.1214/aoms/1177697495.
23.
R. L. Stratonovich, Conditional Markov processes, Theory Probab. Appl., 5 (1960), pp. 156--178, https://doi.org/10.1137/1105015.
24.
S. C. Surace, A. Kutschireiter, and J.-P. Pfister, How to avoid the curse of dimensionality: Scalability of particle filters with and without importance weights, SIAM Rev., 61 (2019), pp. 79--91, https://doi.org/10.1137/17M1125340.
25.
S. C. Surace, A. Kutschireiter, and J.-P. Pfister, Asymptotically exact unweighted particle filter for manifold-valued hidden states and point process observations, IEEE Control Syst. Lett., 4 (2020), pp. 480--485, https://doi.org/10.1109/LCSYS.2019.2951093.
26.
A. Taghvaei and P. G. Mehta, An optimal transport formulation of the linear feedback particle filter, in Proceedings of the American Control Conference (ACC), 2016, pp. 3614--3619, https://doi.org/10.1109/ACC.2016.7525474.
27.
A. Taghvaei and P. G. Mehta, An optimal transport formulation of the ensemble Kalman filter, IEEE Trans. Automat. Control, 66 (2021), pp. 3052--3067, https://doi.org/10.1109/TAC.2020.3015410.
28.
T. Yang, R. S. Laugesen, P. G. Mehta, and S. P. Meyn, Multivariable feedback particle filter, Automatica, 71 (2016), pp. 10--23, https://doi.org/10.1016/j.automatica.2016.04.019.
29.
T. Yang, P. G. Mehta, and S. P. Meyn, Feedback particle filter with mean-field coupling, in Proceedings of the 50th IEEE Conference on Decision and Control and European Control Conference, 2011, pp. 7909--7916.
30.
T. Yang, P. G. Mehta, and S. P. Meyn, Feedback Particle Filter, IEEE Trans. Automat. Control, 58 (2013), pp. 2465--2480.

Information & Authors

Information

Published In

cover image SIAM Journal on Control and Optimization
SIAM Journal on Control and Optimization
Pages: 597 - 619
ISSN (online): 1095-7138

History

Submitted: 30 November 2020
Accepted: 14 November 2021
Published online: 1 March 2022

Keywords

  1. nonlinear filtering
  2. Kushner--Stratonovich equation
  3. Fokker--Planck equation
  4. stochastic differential equations
  5. McKean--Vlasov processes
  6. interacting particle systems
  7. importance sampling

MSC codes

  1. 60G35
  2. 60H15
  3. 65C35
  4. 65C05
  5. 35Q84

Authors

Affiliations

Funding Information

Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung https://doi.org/10.13039/501100001711 : PP00P3 179060, 31003A 175644

Metrics & Citations

Metrics

Citations

If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download.

Cited By

There are no citations for this item

View Options

View options

PDF

View PDF

Media

Figures

Other

Tables

Share

Share

Copy the content Link

Share with email

Email a colleague

Share on social media