Generalised filtering. (English) Zbl 1189.94032
Summary: We describe a Bayesian filtering scheme for nonlinear state-space models in continuous time. This scheme is called Generalised Filtering and furnishes posterior (conditional) densities on hidden states and unknown parameters generating observed data. Crucially, the scheme operates online, assimilating data to optimize the conditional density on time-varying states and time-invariant parameters. In contrast to Kalman and Particle smoothing, Generalised Filtering does not require a backwards pass. In contrast to variational schemes, it does not assume conditional independence between the states and parameters. Generalised Filtering optimises the conditional density with respect to a free-energy bound on the model’s log-evidence. This optimisation uses the generalised motion of hidden states and parameters, under the prior assumption that the motion of the parameters is small. We describe the scheme, present comparative evaluations with a fixed-form variational version, and conclude with an illustrative application to a nonlinear state-space model of brain imaging time-series.
MSC:
| 94A12 | Signal theory (characterization, reconstruction, filtering, etc.) |
| 93E11 | Filtering in stochastic control theory |
| 62M10 | Time series, auto-correlation, regression, etc. in statistics (GARCH) |
| 92C50 | Medical applications (general) |
References:
| [1] | M. S. Arulampalam, S. Maskell, N. Gordon, and T. Clapp, “A tutorial on particle filters for online nonlinear/non-Gaussian Bayesian tracking,” IEEE Transactions on Signal Processing, vol. 50, no. 2, pp. 174-188, 2002. · doi:10.1109/78.978374 |
| [2] | R. var der Merwe, A. Doucet, N. de Freitas, and E. Wan, “The unscented particle filter,” Tech. Rep. CUED/F-INFENG/TR 380, 2000. |
| [3] | K. J. Friston, “Variational filtering,” NeuroImage, vol. 41, no. 3, pp. 747-766, 2008. · doi:10.1016/j.neuroimage.2008.03.017 |
| [4] | K. J. Friston, N. Trujillo-Barreto, and J. Daunizeau, “DEM: a variational treatment of dynamic systems,” NeuroImage, vol. 41, no. 3, pp. 849-885, 2008. · doi:10.1016/j.neuroimage.2008.02.054 |
| [5] | J. Daunizeau, K. J. Friston, and S. J. Kiebel, “Variational Bayesian identification and prediction of stochastic nonlinear dynamic causal models,” Physica D, vol. 238, no. 21, pp. 2089-2118, 2009. · Zbl 1229.62027 · doi:10.1016/j.physd.2009.08.002 |
| [6] | G. L. Eyink, J. M. Restrepo, and F. J. Alexander, “A mean field approximation in data assimilation for nonlinear dynamics,” Physica D, vol. 195, no. 3-4, pp. 347-368, 2004. · Zbl 1081.82019 · doi:10.1016/j.physd.2004.04.003 |
| [7] | C. Archambeau, D. Cornford, M. Opper, and J. Shawe-Taylor, “Gaussian process approximations of stochastic differential equations,” in Proceedings of the Journal of Machine Learning Research Workshop and Conference, vol. 1, pp. 1-16, October 2007. |
| [8] | B. Balaji, “Continuous-discrete path integral filtering,” Entropy, vol. 11, no. 3, pp. 402-430, 2009. · Zbl 1179.35329 · doi:10.3390/e110300402 |
| [9] | V. A. Billock, G. C. de Guzman, and J. A. Scott Kelso, “Fractal time and 1/f spectra in dynamic images and human vision,” Physica D, vol. 148, no. 1-2, pp. 136-146, 2001. · Zbl 1098.92510 · doi:10.1016/S0167-2789(00)00174-3 |
| [10] | J. Carr, Applications of Centre Manifold Theory, vol. 35 of Applied Mathematical Sciences, Springer, New York, NY, USA, 1981. · Zbl 0464.58001 |
| [11] | M. J. Beal and Z. Ghahramani, “The variational Bayesian EM algorithm for incomplete data: with application to scoring graphical model structures,” in Bayesian Statistics, J. M. Bernardo, M. J. Bayarri, J. O. Berger, et al., Eds., chapter 7, Oxford University Press, Oxford, UK, 2003. |
| [12] | G. V. Puskorius and L. A. Feldkamp, “Decoupled extended Kalman filter training of feedforward layered networks,” in Proceedings of the International Joint Conference on Neural Networks (IJCNN ’91), vol. 1, pp. 771-777, 1991. |
| [13] | K. Friston, “Hierarchical models in the brain,” PLoS Computational Biology, vol. 4, no. 11, Article ID e1000211, 24 pages, 2008. · doi:10.1371/journal.pcbi.1000211 |
| [14] | P. Whittle, “Likelihood and cost as path integrals,” Journal of the Royal Statistical Society. Series B, vol. 53, no. 3, pp. 505-538, 1991. · Zbl 0800.62539 |
| [15] | G. L. Eyink, “Action principle in nonequilibrium statistical dynamics,” Physical Review E, vol. 54, no. 4, part A, pp. 3419-3435, 1996. · doi:10.1103/PhysRevE.54.3419 |
| [16] | G. E. Hinton and D. van Camp, “Keeping neural networks simple by minimising the description length of weights,” in Proceedings of the 6th ACM Conference on Computational Learning Theory (COLT ’93), pp. 5-13, Santa Cruz, Calif, USA, July 1993. |
| [17] | D. J. C. MacKay, “Free energy minimisation algorithm for decoding and cryptanalysis,” Electronics Letters, vol. 31, no. 6, pp. 446-447, 1995. · doi:10.1049/el:19950331 |
| [18] | G. L. Eyink, “A variational formulation of optimal nonlinear estimation,” Tech. Rep. LA-UR00-5264, University of Arizona, 2001, http://arxiv.org/abs/physics/0011049. · Zbl 0996.76009 |
| [19] | W. D. Penny, K. E. Stephan, A. Mechelli, and K. J. Friston, “Comparing dynamic causal models,” NeuroImage, vol. 22, no. 3, pp. 1157-1172, 2004. · doi:10.1016/j.neuroimage.2004.03.026 |
| [20] | D. R. Cox and H. D. Miller, The Theory of Stochastic Processes, Methuen, London, UK, 1965. · Zbl 0149.12902 |
| [21] | B. Efron and C. Morris, “Stein’s estimation rule and its competitors-an empirical Bayes approach,” Journal of the American Statistical Association, vol. 68, pp. 117-130, 1973. · Zbl 0275.62005 · doi:10.2307/2284155 |
| [22] | R. E. Kass and D. Steffey, “Approximate Bayesian inference in conditionally independent hierarchical models (parametric empirical Bayes models),” Journal of the American Statistical Association, vol. 84, no. 407, pp. 717-726, 1989. · doi:10.2307/2289653 |
| [23] | S. Zeki, J. D. G. Watson, C. J. Lueck, K. J. Friston, C. Kennard, and R. S. J. Frackowiak, “A direct demonstration of functional specialization in human visual cortex,” Journal of Neuroscience, vol. 11, no. 3, pp. 641-649, 1991. |
| [24] | R. B. Buxton, K. Uluda\?, D. J. Dubowitz, and T. T. Liu, “Modeling the hemodynamic response to brain activation,” NeuroImage, vol. 23, supplement 1, pp. S220-S233, 2004. · doi:10.1016/j.neuroimage.2004.07.013 |
| [25] | J. J. Riera, J. Watanabe, I. Kazuki, et al., “A state-space model of the hemodynamic approach: nonlinear filtering of BOLD signals,” NeuroImage, vol. 21, no. 2, pp. 547-567, 2004. · doi:10.1016/j.neuroimage.2003.09.052 |
| [26] | R. C. Sotero and N. J. Trujillo-Barreto, “Biophysical model for integrating neuronal activity, EEG, fMRI and metabolism,” NeuroImage, vol. 39, no. 1, pp. 290-309, 2008. · doi:10.1016/j.neuroimage.2007.08.001 |
| [27] | R. B. Buxton, E. C. Wong, and L. R. Frank, “Dynamics of blood flow and oxygenation changes during brain activation: the balloon model,” Magnetic Resonance in Medicine, vol. 39, no. 6, pp. 855-864, 1998. · doi:10.1002/mrm.1910390602 |
| [28] | K. J. Friston, L. Harrison, and W. Penny, “Dynamic causal modelling,” NeuroImage, vol. 19, no. 4, pp. 1273-1302, 2003. · doi:10.1016/S1053-8119(03)00202-7 |
| [29] | K. J. Friston and S. J. Kiebel, “Attractors in song,” New Mathematics and Natural Computation, vol. 5, no. 1, pp. 83-114, 2009. · Zbl 1163.92005 · doi:10.1142/S1793005709001209 |
| [30] | T. Ozaki, “A bridge between nonlinear time series models and nonlinear stochastic dynamical systems: a local linearization approach,” Statistica Sinica, vol. 2, no. 1, pp. 113-135, 1992. · Zbl 0820.62075 |
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.
