Advances in Computational Mathematics

, Volume 41, Issue 5, pp 1343–1364 | Cite as

Data-driven combined state and parameter reduction for inverse problems

  • Christian Himpe
  • Mario Ohlberger


In this contribution we present an accelerated optimization-based approach for combined state and parameter reduction of a parametrized forward model, which is used to construct a surrogate model in a Bayesian inverse problem setting. Following the ideas presented in Lieberman et al. (SIAM J. Sci. Comput. 32(5), 2523–2542, 2010), our approach is based on a generalized data-driven optimization functional in the construction process of the reduced order model and the usage of a Monte-Carlo basis enrichment strategy that results in an additional speed-up of the overall method. In principal, the model reduction procedure is based on the offline construction of appropriate low-dimensional state and parameter spaces and an online inversion step using the resulting surrogate model that is obtained through projection of the underlying forward model onto the reduced spaces. The generalizations and enhancements presented in this work are shown to decrease overall computational time and thus allow an application to large-scale problems. Numerical experiments for a generic model and a fMRI connectivity model are presented in order to compare the computational efficiency of our improved method with the original approach.


Model reduction Model order reduction Combined reduction Optimization Greedy 

Mathematics Subject Classifications (2010)

37N40 93A15 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Friston, K.J., Harrison, L., Penny, W.: Dynamic causal modelling. Neuroimage 19(4), 1273–1302 (2003)CrossRefGoogle Scholar
  2. 2.
    Moran, R.J., Kiebel, S.J., Stephan, K.E., Reilly, R.B., Daunizeau, J., Friston, K.J.: A neural mass model of spectral responses in electrophysiology. NeuroImage 37(3), 706–720 (2007)CrossRefGoogle Scholar
  3. 3.
    Stephan, K.E., Friston, K.J.: Models of effective connectivity in neural systems. In: Jirsa, V.K., McIntosh, A.R. (eds.) Handbook of Brain Connectivity, Understanding Complex Systems, pp 303–327. Springer, Berlin Heidelberg (2007)Google Scholar
  4. 4.
    Stuart, A.W.: Inverse problems: A Bayesian perspective. Acta Numer. 19(1), 451–559 (2010)zbMATHMathSciNetCrossRefGoogle Scholar
  5. 5.
    Biegler, L., Biros, G., Ghattas, O., Heinkenschloss, M., Keyes, D., Mallick, B., Tenorio, L., Waanders, B., Willcox, K., Marzouk, Y.: Large-scale inverse problems and quantification of uncertainty. Wiley Series in Computational Statistics. Wiley (2011)Google Scholar
  6. 6.
    Weile, S., Michielssen, E., Grimme, E., Gallivan, K.: A method for generating rational interpolant reduced order models of two- parameter linear systems. Appl. Math. Lett. 12(5), 93–102 (1999)zbMATHMathSciNetCrossRefGoogle Scholar
  7. 7.
    Feng, L., Benner, P.: A robust algorithm for parametric model order reduction. In: PAMM, vol. 7(1), pp. 1021501–1021502 (2007)Google Scholar
  8. 8.
    Baur, U., Benner, P.: Parametrische Modellreduktion mit dünnen Gittern. In: GMA-Fachausschuss 1.30, Modellbildung, Identifizierung und Simulation in der Automatisierungstechnik, Salzburg (2008)Google Scholar
  9. 9.
    Lohmann, B., Eid, R.: Efficient order reduction of parametric and nonlinear models by superposition of locally reduced models. In: Methoden und Anwendungen der Regelungstechnik. Erlangen-Münchener Workshops 2007 und 2008. Shaker Verlag, Aachen (2009)Google Scholar
  10. 10.
    Eid, R., Castañé-Selga, R., Panzer, H., Wolf, T., Lohmann, B.: Stability-preserving parametric model reduction by matrix interpolation. Math. Comp. Model. Dyn. 17(4), 319–335 (2011)zbMATHCrossRefGoogle Scholar
  11. 11.
    Amsallem, D., Farhat, C.: An online method for interpolating linear parametric reduced-order models. SIAM J. Sci. Comput. 33(5), 2169–2198 (2011)zbMATHMathSciNetCrossRefGoogle Scholar
  12. 12.
    Haasdonk, B., Ohlberger, M.: Reduced basis method for finite volume approximations of parametrized linear evolution equations. M2AN 42(2), 277–302 (2008)zbMATHMathSciNetCrossRefGoogle Scholar
  13. 13.
    Haasdonk, B.: Convergence rates of the POD-greedy method. M2AN 47(3), 859–873 (2013)zbMATHMathSciNetCrossRefGoogle Scholar
  14. 14.
    Haasdonk, B., Ohlberger, M.: Efficient reduced models and a posteriori error estimation for parametrized dynamical systems by offline/online decomposition. Math. Comp. Model. Dyn. 17(2), 145–161 (2011)zbMATHMathSciNetCrossRefGoogle Scholar
  15. 15.
    Nguyen, N.C., Rozza, G., Huynh, D.B.P., Patera, A.T.: Reduced basis approximation and a posteriori error estimation for parametrized parabolic PDEs: application to real-time Bayesian parameter estimation. In: Large-Scale Inverse Problems and Quantification of Uncertainty, Wiley Ser. Comput. Stat., pp. 151–178. Wiley (2010)Google Scholar
  16. 16.
    Himpe, C., Ohlberger, M.: Cross-Gramian based combined state and parameter reduction for large-scale control systems. Math. Problem Eng. 2014, 1–13 (2014)MathSciNetCrossRefGoogle Scholar
  17. 17.
    Lieberman, C., Willcox, K., Ghattas, O.: Parameter and state model reduction for large-scale statistical inverse problems. SIAM J. Sci. Comput. 32(5), 2523–2542 (2010)zbMATHMathSciNetCrossRefGoogle Scholar
  18. 18.
    Bui-Thanh, T., Willcox, K., Ghattas, O., van Bloemen Waanders, B.: Goal-oriented, model-constrained optimization for reduction of large-scale systems. J. Comput. Phys. 224(2), 880–896 (2007)zbMATHMathSciNetCrossRefGoogle Scholar
  19. 19.
    Bui-Thanh, T., Willcox, K., Ghattas, O.: Model reduction for large-scale systems with high-dimensional parametric input space. SIAM J. Sci. Comput. 30(6), 3270–3288 (2008)zbMATHMathSciNetCrossRefGoogle Scholar
  20. 20.
    Bui-Thanh, T., Burstedde, C., Ghattas, O., Martin, J., Stadler, G., Wilcox, L.C.: Extreme-scale UQ for Bayesian inverse problems governed by PDEs. In: Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis, pp. 1–11 (2012)Google Scholar
  21. 21.
    Bashir, O., Willcox, K., Ghattas, O., van Bloemen Waanders, B., Hill, J.: Hessian-based model reduction for large-scale systems with initial-condition inputs. Int. J. Numer. Meth. Engng. 73(6), 844–868 (2008)zbMATHMathSciNetCrossRefGoogle Scholar
  22. 22.
    Flath, H.P., Wilcox, L.C., Akcelik, V., Hill, J., van Bloemen Waanders, B., Ghattas, O.: Fast algorithms for Bayesian uncertainty quantification in large-scale linear inverse problems based on low-rank partial Hessian approximations. SIAM J. Sci. Comput. 33(1), 407–432 (2011)zbMATHMathSciNetCrossRefGoogle Scholar
  23. 23.
    Lieberman, C., Willcox, K.: Goal-oriented inference: Approach, linear theory, and application to advection diffusion. SIAM J. Sci. Comput. 34(4), A1880–A1904 (2012)zbMATHMathSciNetCrossRefGoogle Scholar
  24. 24.
    Lieberman, C., Van Bloemen Waanders, B: Hessian-based model reduction approach to solving large-scale source inversion problems. In: CSRI Summer Proceedings 2007, pp. 37–48 (2007)Google Scholar
  25. 25.
    Martin, A., Grepl, Krcher, M.: Reduced basis a posteriori error bounds for parametrized linear-quadratic elliptic optimal control problems. Comptes Rendus Mathematique 349(15–16), 873–877 (2011)zbMATHGoogle Scholar
  26. 26.
    Himpe, C.: {optmor} - optimization-based model order reduction (Version 1.2). doi: 10.5281/zenodo.17796 (2014)
  27. 27.
    Octave Community. GNU Octave 3.8. (2014)
  28. 28.
    MATLAB. The MathWorks Inc., Natick, Massachusetts (2014)Google Scholar
  29. 29.
    Kamrani, E., Foroushani, A., Vaziripour, M., Sawan, M.: Detecting the stable, observable and controllable states of the human brain dynamics. OJMI 2(4), 128–136 (2012)CrossRefGoogle Scholar
  30. 30.
    Galbally, D., Fidkowski, K., Willcox, K., Ghattas, O.: Non-linear model reduction for uncertainty quantification in large-scale inverse problems. Int. J. Numer. Meth. Engng. 81(12), 1581–1608 (2010)zbMATHMathSciNetGoogle Scholar

Copyright information

© Springer Science+Business Media New York 2015

Authors and Affiliations

  1. 1.Institute for Computational and Applied MathematicsUniversity of MünsterMünsterGermany

Personalised recommendations