New Theory and Numerical Results for Gromov's Method for Stochastic Particle Flow Filters

We derive a new exact stochastic particle flow for Bayes' rule using a theorem of Gromov. We also show numerical experiments for high dimensional problems up to $\mathbf{d}=100$. The accuracy of our new filter is many orders of magnitude better than standard particle filters, and our filter beats the EKF by orders of magnitude for difficult nonlinear problems. The new theoretical result is valid for arbitrary smooth nowhere vanishing densities, whereas our previous theory was derived for the special case of Gaussian densities with linear measurements. It is crucial to mitigate stiffness of the flow in order to achieve good numerical results.

[1]  Yunpeng Li,et al.  Fast particle flow particle filters via clustering , 2016, 2016 19th International Conference on Information Fusion (FUSION).

[2]  Kristine L. Bell,et al.  Implementation of the homotopy particle filter in the JPDA and MAP-PF multi-target tracking algorithms , 2014, 17th International Conference on Information Fusion (FUSION).

[3]  Yunpeng Li,et al.  Particle Filtering With Invertible Particle Flow , 2016, IEEE Transactions on Signal Processing.

[4]  Gareth W. Peters,et al.  Langevin and Hamiltonian Based Sequential MCMC for Efficient Bayesian Filtering in High-Dimensional Spaces , 2015, IEEE Journal of Selected Topics in Signal Processing.

[5]  Fred Daum,et al.  Particle flow with non-zero diffusion for nonlinear filters , 2013, Defense, Security, and Sensing.

[6]  Jiqiang Guo,et al.  Stan: A Probabilistic Programming Language. , 2017, Journal of statistical software.

[7]  A. Doucet,et al.  Gibbs flow for approximate transport with applications to Bayesian computation , 2015, Journal of the Royal Statistical Society: Series B (Statistical Methodology).

[8]  Simon J. Godsill,et al.  Gaussian flow sigma point filter for nonlinear Gaussian state-space models , 2017, 2017 20th International Conference on Information Fusion (Fusion).

[9]  Yang Liu,et al.  Non-Zero Diffusion Particle Flow SMC-PHD Filter for Audio-Visual Multi-Speaker Tracking , 2018, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[10]  Nima Moshtagh,et al.  Homotopy Particle Filter for Ground-Based Tracking of Satellites at GEO , 2016 .

[11]  Junjie Wang,et al.  Distributed Particle Flow Filter for Target Tracking in Wireless Sensor Networks , 2018, J. Sensors.

[12]  Uwe D. Hanebeck,et al.  Progressive Gaussian filter using importance sampling and particle flow , 2016, 2016 19th International Conference on Information Fusion (FUSION).

[13]  Fred Daum,et al.  Generalized Gromov method for stochastic particle flow filters , 2017, Defense + Security.

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

[15]  Jiande Wu,et al.  Parallel Computing of Particle Filtering Algorithms for Target Tracking Applications , 2014 .

[16]  Martin Ulmke,et al.  Improvements in the implementation of log-homotopy based particle flow filters , 2015, 2015 18th International Conference on Information Fusion (Fusion).

[17]  Pete Bunch,et al.  Approximations of the Optimal Importance Density Using Gaussian Particle Flow Importance Sampling , 2014, 1406.3183.

[18]  Fred Daum,et al.  Particle degeneracy: root cause and solution , 2011, Defense + Commercial Sensing.

[19]  Alfred O. Hero,et al.  A Survey of Stochastic Simulation and Optimization Methods in Signal Processing , 2015, IEEE Journal of Selected Topics in Signal Processing.

[20]  Branko Ristic,et al.  Beyond the Kalman Filter: Particle Filters for Tracking Applications , 2004 .

[21]  Chris Kreucher,et al.  A geodesic flow particle filter for non-thresholded measurements , 2017, 2017 IEEE Radar Conference (RadarConf).

[22]  Khan Muhammad Altamash,et al.  A log homotopy based particle flow solution for mixture of Gaussian prior densities , 2016 .

[23]  Torsten Bertram,et al.  On the Use of Particle Flow to Enhance the Computational Performance of Particle-Filtering-based Prognostics , 2014 .

[24]  Shozo Mori,et al.  Adaptive step size approach to homotopy-based particle filtering Bayesian update , 2016, 2016 19th International Conference on Information Fusion (FUSION).

[25]  Piyush Grover,et al.  Efficient estimation and uncertainty quantification in space mission dynamics , 2012 .

[26]  Lingling Zhao,et al.  Particle flow auxiliary particle filter , 2015, 2015 IEEE 6th International Workshop on Computational Advances in Multi-Sensor Adaptive Processing (CAMSAP).

[27]  Christian P. Robert,et al.  Bayesian computation: a perspective on the current state, and sampling backwards and forwards , 2015, 1502.01148.

[28]  Mark R. Morelande,et al.  Optimal posterior density approximation for bearings-only tracking , 2012, 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

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

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

[31]  J. Huang,et al.  Curse of dimensionality and particle filters , 2003, 2003 IEEE Aerospace Conference Proceedings (Cat. No.03TH8652).

[32]  Christian Musso,et al.  Improving Regularised Particle Filters , 2001, Sequential Monte Carlo Methods in Practice.

[33]  Tao Ding,et al.  Implementation of the Daum-Huang exact-flow particle filter , 2012, 2012 IEEE Statistical Signal Processing Workshop (SSP).

[34]  Fred Daum,et al.  Seven dubious methods to mitigate stiffness in particle flow with non-zero diffusion for nonlinear filters, Bayesian decisions, and transport , 2014, Defense + Security Symposium.

[35]  Peter Willett,et al.  Discussion and application of the homotopy filter , 2011, Defense + Commercial Sensing.

[36]  Uwe D. Hanebeck,et al.  Progressive Bayes: a new framework for nonlinear state estimation , 2003, SPIE Defense + Commercial Sensing.

[37]  Raphael Douady,et al.  Optimal Transport Filtering with Particle Reweighing in Finance , 2017 .

[38]  Frederick E. Daum,et al.  Particle flow for nonlinear filters, Bayesian decisions and transport , 2013, Proceedings of the 16th International Conference on Information Fusion.

[39]  Fred Daum,et al.  Stochastic Particle Flow for Nonlinear High-Dimensional Filtering Problems , 2015, 1511.01448.

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

[41]  Yuxin Zhao,et al.  Particle flow for sequential Monte Carlo implementation of probability hypothesis density , 2017, 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[42]  Frederick E. Daum,et al.  Gromov's method for Bayesian stochastic particle flow: A simple exact formula for Q , 2016, 2016 IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems (MFI).