Journal of Signal Processing Systems

, Volume 61, Issue 1, pp 51–59 | Cite as

A Comparison of Variational and Markov Chain Monte Carlo Methods for Inference in Partially Observed Stochastic Dynamic Systems

  • Yuan Shen
  • Cedric Archambeau
  • Dan Cornford
  • Manfred Opper
  • John Shawe-Taylor
  • Remi Barillec
Article

Abstract

In recent work we have developed a novel variational inference method for partially observed systems governed by stochastic differential equations. In this paper we provide a comparison of the Variational Gaussian Process Smoother with an exact solution computed using a Hybrid Monte Carlo approach to path sampling, applied to a stochastic double well potential model. It is demonstrated that the variational smoother provides us a very accurate estimate of mean path while conditional variance is slightly underestimated. We conclude with some remarks as to the advantages and disadvantages of the variational smoother.

Keywords

Data assimilation Signal processing Nonlinear smoothing Variational approximation Bayesian computation 

References

  1. 1.
    Honerkamp, J. (1994). Stochastic dynamical systems. New York: VCH.Google Scholar
  2. 2.
    Wilkinson, D. J. (2006). Stochastic modelling for system biology. Boca Raton: Chapman & Hall/CRC.Google Scholar
  3. 3.
    Kalnay, E. (2003). Atmospheric modeling, data assimilation and predictability. Cambridge: Cambridge University Press.Google Scholar
  4. 4.
    Anderson, B. D. O., & Moore, J. B. (2005). Optimal filtering. Mineola: Dover.MATHGoogle Scholar
  5. 5.
    Kushner, H. J. (1967). Dynamical equations for optimal filter. Journal of Differential Equations, 3, 179–190.MATHCrossRefMathSciNetGoogle Scholar
  6. 6.
    Stratonovich, R. L. (1960) Conditional markov processes. Theory of Probability and Its Applications, 5, 156–178.CrossRefGoogle Scholar
  7. 7.
    Pardoux, E. (1982). Équations du filtrage non linéaire de la prédiction et du lissage. Stochastics, 6, 193–231.MATHMathSciNetGoogle Scholar
  8. 8.
    Kalman, R. E., & Bucy, R. S. (1961). New results in linear filtering and prediction theory. Journal of Basic Engineering, 83D, 95–108.MathSciNetGoogle Scholar
  9. 9.
    Shumway, R. H., & Stoffer, D. S. (2000). Time series analysis and its applications. New York: Springer.MATHGoogle Scholar
  10. 10.
    Archambeau, C., Cornford, D., Opper, M., & Shawe-Tayler, J. (2007). Gaussian process approximations of stochastic differential equations. Journal of Machine Learning Research Workshop and Conference Proceedings, 1, 1–16.Google Scholar
  11. 11.
    Klöden, P. E., & Platen, E. (1992). Numerical solution of stochastic differential equations. Berlin: Spinger.MATHGoogle Scholar
  12. 12.
    Andrieu, C., De Freitas, N., Doucet, A., & Jordan, M. I. (2003). An introduction to MCMC for machine learning. Machine Learning, 50, 5–43.MATHCrossRefGoogle Scholar
  13. 13.
    Hürzler, M. (1998). Statistical methods for general state-space models. PhD Thesis Nr. 12674, ETH Zürich.Google Scholar
  14. 14.
    Alexander, F. J., Eyink, G. L., & Restrepo, J. M. (2005). Accelerated Monte Carlo for optimal estimation of time series. Journal of Statistical Physics, 119, 1331–1345.MATHCrossRefGoogle Scholar
  15. 15.
    Gelb, A. (1974). Applied optimal estimation. Cambridge: MIT.Google Scholar
  16. 16.
    Evensen, G. (1992). Using the extended Kalman filter with a multilayer quasi-geostrophic ocean model. Journal of Geophysical Research, 97, 17905–17924.CrossRefGoogle Scholar
  17. 17.
    Evensen, G. (1994). Sequential data assimilation with a non-linear quasi-geostrophic model using Monte Carlo methods to forecast error statistics. Journal of Geophysical Research, 99, 10143–10162.CrossRefGoogle Scholar
  18. 18.
    Kitagawa, G. (1987). Non-Gaussian state space modelling of non-stationary time series. Journal of the American Statistical Association, 82, 503–514.MathSciNetGoogle Scholar
  19. 19.
    Kullback, S., & Leibler, R. A. (1951). On information and sufficiency. Annal of Mathematical Statistics, 22, 79–86.MATHCrossRefMathSciNetGoogle Scholar
  20. 20.
    Jaakkola, T. S. (2001). Tutorial on variational approximation methods. In D. Saad, & M. Opper (Eds.), Advanced mean field methods. Cambridge: MIT.Google Scholar
  21. 21.
    Crisan, D., Del Moral, P., & Lyons, T. J. (1999). Interacting particle systems approximations of the Kushner-Stratonovich equation. Advances in Applied Probability, 31, 819–838.MATHCrossRefMathSciNetGoogle Scholar
  22. 22.
    Rasmussen, C. E., & Williams, C. K. I. (2006). Gaussian process for machine learning. Cambridge: MIT.Google Scholar
  23. 23.
    Miller, R. N., Carter, E. F, & Blue, S. T. (1999). Data assimilation into nonlinear stochastic models. Tellus, 51A, 167–194.Google Scholar
  24. 24.
    Chan, G., & Wood, A. T. A. (1999). Simulation of stationary Gaussian vector fields. Statistics and Computing, 22, 265–268.CrossRefGoogle Scholar
  25. 25.
    Eyink, G. L., Restrepo, J. M., & Alexander, F. J. (2004). A mean-field approximation in data assimilation for nonlinear dynamics. Physica D, 194, 347–368.CrossRefMathSciNetGoogle Scholar
  26. 26.
    Julier, S. J., Uhlmann, J., & Durrant-Whyte, H. F. (2000). A new method for the nonlinear tranformation of means and covariances in filters and estimators. IEEE Transactions on Automatic Control, 45, 477–482.MATHCrossRefMathSciNetGoogle Scholar
  27. 27.
    Kitagawa, G. (1994). The two-filter formula for smoothing and an implementation of the Gaussian-sum smoother. Annals of the Institute of Statistical Mathematics, 46(4), 605–623.MATHCrossRefMathSciNetGoogle Scholar
  28. 28.
    Alspach, D. L., & Sorenson, H. W. (1972). Nonlinear Bayesian estimation using Gaussian sum approximations. IEEE Transactions On Automatic Control, 17(4) 439–448.MATHCrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC 2008

Authors and Affiliations

  • Yuan Shen
    • 1
  • Cedric Archambeau
    • 2
  • Dan Cornford
    • 1
  • Manfred Opper
    • 3
  • John Shawe-Taylor
    • 2
  • Remi Barillec
    • 1
  1. 1.Neural Computing Research GroupAston UniversityBirminghamUK
  2. 2.Department of Computer ScienceUniversity College LondonLondonUK
  3. 3.Artificial Intelligence GroupTechnical University BerlinBerlinGermany

Personalised recommendations