Eigendecompositions of Transfer Operators in Reproducing Kernel Hilbert Spaces

Abstract

Transfer operators such as the Perron–Frobenius or Koopman operator play an important role in the global analysis of complex dynamical systems. The eigenfunctions of these operators can be used to detect metastable sets, to project the dynamics onto the dominant slow processes, or to separate superimposed signals. We propose kernel transfer operators, which extend transfer operator theory to reproducing kernel Hilbert spaces and show that these operators are related to Hilbert space representations of conditional distributions, known as conditional mean embeddings. The proposed numerical methods to compute empirical estimates of these kernel transfer operators subsume existing data-driven methods for the approximation of transfer operators such as extended dynamic mode decomposition and its variants. One main benefit of the presented kernel-based approaches is that they can be applied to any domain where a similarity measure given by a kernel is available. Furthermore, we provide elementary results on eigendecompositions of finite-rank RKHS operators. We illustrate the results with the aid of guiding examples and highlight potential applications in molecular dynamics as well as video and text data analysis.

This is a preview of subscription content, log in to check access.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9

Notes

  1. 1.

    Although this term is commonly used in the literature, \( \Phi \) is technically not a matrix, but a row vector in \( \mathbb {H}^n \). If \(\mathbb {H}\) is finite dimensional, \( \Phi \) can be viewed as a matrix.

  2. 2.

    For specific choices of \(\mathbb {P}(X)\) and \(\mathbb {P}(Y)\), the boundedness assumption can be replaced by a more general integrability assumption, i.e., \(\mathbb {E}_{\scriptscriptstyle X}[k(X,X)] < \infty \) and \(\mathbb {E}_{\scriptscriptstyle Y}[l(Y,Y)] < \infty \), so that \(\mathbb {H} \subset L^2({\mathbb {X}}, \mathbb {P}(X))\) and \(\mathbb {\mathbb {G}} \subset L^2({\mathbb {Y}}, \mathbb {P}(Y))\), respectively.

  3. 3.

    An observable could be, for example, a measurement or sensor probe.

  4. 4.

    This holds, for instance, for finite domains equipped with characteristic kernels, but not necessarily for continuous domains (Song et al. 2013).

  5. 5.

    See, e.g., Kloeden and Platen (2011).

  6. 6.

    ScienceOnline: The Pendulum and Galileo.

  7. 7.

    Reuters: French opposition, Twitter users slam Macron’s anti-fake-news plans.

  8. 8.

    Parts of the same articles are used several times to increase the size of the data set, this is thus a synthetic example, mainly to illustrate the concept.

  9. 9.

    We use the String Kernel Software implementation.

References

  1. Bach, F.R., Jordan, M.I.: Kernel independent component analysis. J. Mach. Learn. Res. 3, 1–48 (2003)

    MathSciNet  MATH  Google Scholar 

  2. Baker, C.: Mutual information for Gaussian processes. SIAM J. Appl. Math. 19(2), 451–458 (1970)

    MathSciNet  MATH  Google Scholar 

  3. Baker, C.: Joint measures and cross-covariance operators. Trans. Am. Math. Soc. 186, 273–289 (1973)

    MathSciNet  MATH  Google Scholar 

  4. Baxter, J.R., Rosenthal, J.S.: Rates of convergence for everywhere-positive Markov chains. Stat. Probab. Lett. 22(4), 333–338 (1995)

    MathSciNet  MATH  Google Scholar 

  5. Berlinet, A., Thomas-Agnan, C.: Reproducing Kernel Hilbert Spaces in Probability and Statistics. Kluwer Academic Publishers, Berlin (2004)

    Google Scholar 

  6. Berry, T., Giannakis, D., Harlim, J.: Nonparametric forecasting of low-dimensional dynamical systems. Phys. Rev. E 91, 032915 (2015). https://doi.org/10.1103/PhysRevE.91.032915

    Article  Google Scholar 

  7. Bittracher, A., Koltai, P., Klus, S., Banisch, R., Dellnitz, M., Schütte, C.: Transition manifolds of complex metastable systems: theory and data-driven computation of effective dynamics. Accepted for publication in JNLS, (2017)

  8. Bo, L., Ren, X., Fox, D.: Kernel descriptors for visual recognition. In J. D. Lafferty, C. K. I. Williams, J. Shawe-Taylor, R. S. Zemel, and A. Culotta, editors, Advances in Neural Information Processing Systems 23, pages 244–252. Curran Associates, Inc., (2010)

  9. Brunton, S.L., Brunton, B.W., Proctor, J.L., Kutz, J.N.: Koopman invariant subspaces and finite linear representations of nonlinear dynamical systems for control. PLoS ONE 11(2), 1–19 (2016)

    Google Scholar 

  10. Case, D.A., Berryman, J.T., Betz, R.M., Cerutti, D.S., Cheatham, T.E., Darden, T.A., Duke, R.E., Giese, T.J., Gohlke, H., Goetz, A.W., Homeyer, N., Izadi, S., Janowski, P., Kaus, J., Kovalenko, A., Lee, T.S., LeGrand, S., Li, P., Luchko, T., Luo, R., Madej, B., Merz, K.M., Monard, G., Needham, P., Nguyen, H., Nguyen, H.T., Omelyan, I., Onufriev, A., Roe, D.R., Roitberg, A., Salomon-Ferrer, R., Simmerling, C.L., Smith, W., Swails, J., Walker, R.C., Wang, J., Wolf, R.M., Wu, X., York, D.M., Kollman, P.A.: AMBER 2015. University of California, San Francisco (2015)

  11. Diestel, J., Uhl, J.J.: Vector Measures. American Mathematical Society, Providence (1977)

    Google Scholar 

  12. Dinculeanu, N.: Vector Integration and Stochastic Integration in Banach Spaces. Wiley, Hoboken (2000)

    Google Scholar 

  13. Fukumizu, K., Bach, F.R., Jordan, M.I.: Dimensionality reduction for supervised learning with Reproducing Kernel Hilbert Spaces. J. Mach. Learn. Res. 5, 73–99 (2004)

    MathSciNet  MATH  Google Scholar 

  14. Fukumizu, K., Bach, F., Gretton, A.: Statistical consistency of kernel canonical correlation analysis. J. Mach. Learn. Res. 8, 361–383 (2007a)

    MathSciNet  MATH  Google Scholar 

  15. Fukumizu, K., Song, L., Gretton, A.: Kernel Bayes’ rule: Bayesian inference with positive definite kernels. J. Mach. Learn. Res. 14, 3753–3783 (2013)

    MathSciNet  MATH  Google Scholar 

  16. Giannakis, D., Das, S., Slawinska, J.: Reproducing kernel Hilbert space compactification of unitary evolution groups. arXiv e-prints, (2018)

  17. Grünewälder, S., Lever, G., Gretton, A., Baldassarre, L., Patterson, S., Pontil, M.: Conditional mean embeddings as regressors. In: Proceedings of the 29th International Conference on Machine Learning (ICML), (2012)

  18. Hofmann, T., Schölkopf, B., Smola, A.: Kernel methods in machine learning. Ann. Stat. 36(3), 1171–1220 (2008)

    MathSciNet  MATH  Google Scholar 

  19. Huisinga, W.: Metastability of Markovian systems: a transfer operator based approach in application to molecular dynamics. PhD thesis, Freie Universität Berlin (2001)

  20. Kato, T.: Perturbation Theory for Linear Operators. Springer, Berlin (1980)

    Google Scholar 

  21. Kawahara, Y.: Dynamic mode decomposition with reproducing kernels for Koopman spectral analysis. In: Advances in Neural Information Processing Systems 29, pp. 911–919. Curran Associates, Inc., (2016)

  22. Kloeden, P.E., Platen, E.: Numerical Solution of Stochastic Differential Equations. Stochastic Modelling and Applied Probability. Springer, Berlin (2011)

  23. Klus, S., Koltai, P., Schütte, C.: On the numerical approximation of the Perron–Frobenius and Koopman operator. J. Comput. Dyn. 3(1), 51–79 (2016)

    MathSciNet  MATH  Google Scholar 

  24. Klus, S., Nüske, F., Koltai, P., Wu, H., Kevrekidis, I., Schütte, C., Noé, F.: Data-driven model reduction and transfer operator approximation. J. Nonlinear Sci. 28, 985–1010 (2018a). https://doi.org/10.1007/s00332-017-9437-7

    MathSciNet  Article  MATH  Google Scholar 

  25. Klus, S., Bittracher, A., Schuster, I., Schütte, C.: A kernel-based approach to molecular conformation analysis. J. Chem. Phys. 149, 244109 (2018b)

    Google Scholar 

  26. Klus, S., Peitz, S., Schuster, I.: Analyzing high-dimensional time-series data using kernel transfer operator eigenfunctions. ArXiv e-prints, (2018c)

  27. Korda, M., Mezić, I.: On convergence of extended dynamic mode decomposition to the Koopman operator. J. Nonlinear Sci. 28(2), 687–710 (2018)

    MathSciNet  MATH  Google Scholar 

  28. Lasota, A., Mackey, M. C.: Chaos, fractals, and noise: Stochastic aspects of dynamics, volume 97 of Applied Mathematical Sciences. Springer, 2nd edition, (1994)

  29. Lodhi, H., Saunders, C., Shawe-Taylor, J., Cristianini, N., Watkins, C.: Text classification using string kernels. J. Mach. Learn. Res. 2, 419–444 (2002)

    MATH  Google Scholar 

  30. McGibbon, R.T., Pande, V.S.: Variational cross-validation of slow dynamical modes in molecular kinetics. J. Chem. Phy. 142(12), 124105 (2015)

    Google Scholar 

  31. Molgedey, L., Schuster, H.G.: Separation of a mixture of independent signals using time delayed correlations. Phys. Rev. Lett. 72, 3634–3637 (1994)

    Google Scholar 

  32. Muandet, K., Fukumizu, K., Sriperumbudur, B., Schölkopf, B.: Kernel mean embedding of distributions: a review and beyond. Found. Trends Mach. Learn. 10(1–2), 1–141 (2017)

    MATH  Google Scholar 

  33. Noé, F., Nüske, F.: A variational approach to modeling slow processes in stochastic dynamical systems. Multiscale Model. Simul. 11(2), 635–655 (2013)

    MathSciNet  MATH  Google Scholar 

  34. Nüske, F., Keller, B.G., Pérez-Hernández, G., Mey, A.S.J.S., Noé, F.: Variational approach to molecular kinetics. J. Chem. Theory Comput. 10(4), 1739–1752 (2014)

    Google Scholar 

  35. Pérez-Hernández, G., Paul, F., Giorgino, T., De Fabritiis, G., Noé, F.: Identification of slow molecular order parameters for Markov model construction. J. Chem. Phys. 139(1), 015102 (2013)

    Google Scholar 

  36. Rowley, C.W., Mezić, I., Bagheri, S., Schlatter, P., Henningson, D.S.: Spectral analysis of nonlinear flows. J. Fluid Mech. 641, 115–127 (2009)

    MathSciNet  MATH  Google Scholar 

  37. Schmid, P.J.: Dynamic mode decomposition of numerical and experimental data. J. Fluid Mech. 656, 5–28 (2010)

    MathSciNet  MATH  Google Scholar 

  38. Schölkopf, B., Smola, A.J.: Learning with Kernels: Support Vector Machines, Regularization, Optimization and Beyond. MIT Press, Cambridge (2001)

    Google Scholar 

  39. Schölkopf, B., Smola, A., Müller, K.-R.: Nonlinear component analysis as a kernel eigenvalue problem. Neural Comput. 10(5), 1299–1319 (1998)

    Google Scholar 

  40. Schuster, I., Mollenhauer, M., Klus, S., Muandet, K.: Kernel conditional density operators. arXiv e-prints, (2019)

  41. Schütte, C.: Conformational dynamics: modelling, theory, algorithm, and application to biomolecules. Habilitation Thesis (1999)

  42. Schütte, C., Sarich, M.: Metastability and Markov State Models in Molecular Dynamics: Modeling, Analysis, Algorithmic Approaches. Number 24 in Courant Lecture Notes. American Mathematical Society (2013)

  43. Schwantes, C.R., Pande, V.S.: Modeling molecular kinetics with tICA and the kernel trick. J. Chem. Theory Comput. 11(2), 600–608 (2015)

    Google Scholar 

  44. Sejdinovic, D., Strathmann, H., Garcia, M.L., Andrieu, C., Gretton, A.: Kernel adaptive Metropolis–Hastings. In: International conference on machine learning, pp. 1665–1673 (2014)

  45. Smola, A., Gretton, A., Song, L., Schölkopf, B.: A Hilbert space embedding for distributions. In: Proceedings of the 18th International Conference on Algorithmic Learning Theory, pp. 13–31. Springer, Berlin (2007)

    Google Scholar 

  46. Song, L., Huang, J., Smola, A., Fukumizu, K.: Hilbert space embeddings of conditional distributions with applications to dynamical systems. In: Proceedings of the 26th Annual International Conference on Machine Learning, pp. 961–968 (2009)

  47. Song, L., Fukumizu, K., Gretton, A.: Kernel embeddings of conditional distributions: a unified kernel framework for nonparametric inference in graphical models. IEEE Signal Process. Mag. 30(4), 98–111 (2013)

    Google Scholar 

  48. Sriperumbudur, B., Gretton, A., Fukumizu, K., Lanckriet, G., Schölkopf, B.: Injective Hilbert space embeddings of probability measures. In: The 21st Annual Conference on Learning Theory, pp. 111–122. Omnipress (2008)

  49. Steinwart, I., Christmann, A.: Support Vector Machines, 1st edn. Springer Publishing Company, Incorporated, Berlin (2008)

    Google Scholar 

  50. Tu, J.H., Rowley, C.W., Luchtenburg, D.M., Brunton, S.L., Kutz, J.N.: On dynamic mode decomposition: theory and applications. J. Comput. Dyn. 1(2), 391 (2014)

    MathSciNet  MATH  Google Scholar 

  51. Ulam, S .M.: A Collection of Mathematical Problems. Interscience Publisher, New York (1960)

    Google Scholar 

  52. Williams, M.O., Kevrekidis, I.G., Rowley, C.W.: A data-driven approximation of the Koopman operator: extending dynamic mode decomposition. J. Nonlinear Sci. 25(6), 1307–1346 (2015a)

    MathSciNet  MATH  Google Scholar 

  53. Williams, M.O., Rowley, C.W., Kevrekidis, I.G.: A kernel-based method for data-driven Koopman spectral analysis. J. Comput. Dyn. 2(2), 247–265 (2015b)

    MathSciNet  MATH  Google Scholar 

Download references

Acknowledgements

This research has been partially funded by Deutsche Forschungsgemeinschaft (DFG) through grant CRC 1114 “Scaling Cascades in Complex Systems”. Krikamol Muandet acknowledges fundings from the Faculty of Science, Mahidol University and the Thailand Research Fund (TRF). We would like to thank the reviewers for their helpful comments.

Author information

Affiliations

Authors

Corresponding author

Correspondence to Stefan Klus.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Communicated by Dr. Anthony Bloch.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Klus, S., Schuster, I. & Muandet, K. Eigendecompositions of Transfer Operators in Reproducing Kernel Hilbert Spaces. J Nonlinear Sci 30, 283–315 (2020). https://doi.org/10.1007/s00332-019-09574-z

Download citation

Keywords

  • Reproducing kernel Hilbert spaces
  • Koopman operator
  • Perron–Frobenius operator
  • Eigendecompositions
  • Kernel mean embeddings

Mathematics Subject Classification

  • 37M10
  • 46E22
  • 34L16
  • 37L65