Metric on Nonlinear Dynamical Systems with Koopman Operators

The development of a metric for structural data is a long-term problem in pattern recognition and machine learning. In this paper, we develop a general metric for comparing nonlinear dynamical systems that is defined with Koopman operator in reproducing kernel Hilbert spaces. Our metric includes the existing fundamental metrics for dynamical systems, which are basically defined with principal angles between some appropriately-chosen subspaces, as its special cases. We also describe the estimation of our metric from finite data. We empirically illustrate our metric with an example of rotation dynamics in a unit disk in a complex plane, and evaluate the performance with real-world time-series data.

[1]  Louis Sucheston,et al.  On existence of finite invariant measures , 1964 .

[2]  Naoya Takeishi,et al.  Subspace dynamic mode decomposition for stochastic Koopman analysis. , 2017, Physical review. E.

[3]  Bart De Moor,et al.  Subspace angles between ARMA models , 2002, Syst. Control. Lett..

[4]  Richard J. Martin.  A metric for ARMA processes , 2000, IEEE Trans. Signal Process..

[5]  Bingni W. Brunton,et al.  Extracting spatial–temporal coherent patterns in large-scale neural recordings using dynamic mode decomposition , 2014, Journal of Neuroscience Methods.

[6]  Alexander J. Smola,et al.  Binet-Cauchy Kernels on Dynamical Systems and its Application to the Analysis of Dynamic Scenes , 2007, International Journal of Computer Vision.

[7]  Heni Ben Amor,et al.  Estimation of perturbations in robotic behavior using dynamic mode decomposition , 2015, Adv. Robotics.

[8]  Joshua L. Proctor,et al.  Discovering dynamic patterns from infectious disease data using dynamic mode decomposition , 2015, International health.

[9]  Clarence W. Rowley,et al.  A Data–Driven Approximation of the Koopman Operator: Extending Dynamic Mode Decomposition , 2014, Journal of Nonlinear Science.

[10]  I. Mezić.  Spectral Properties of Dynamical Systems, Model Reduction and Decompositions , 2005 .

[11]  Steven L. Brunton,et al.  Multiresolution Dynamic Mode Decomposition , 2015, SIAM J. Appl. Dyn. Syst..

[12]  René Vidal,et al.  Initial-state invariant Binet-Cauchy kernels for the comparison of Linear Dynamical Systems , 2013, 52nd IEEE Conference on Decision and Control.

[13]  I. Mezić,et al.  Spectral analysis of nonlinear flows , 2009, Journal of Fluid Mechanics.

[14]  B. O. Koopman,et al.  Hamiltonian Systems and Transformation in Hilbert Space. , 1931, Proceedings of the National Academy of Sciences of the United States of America.

[15]  Steven L. Brunton,et al.  Dynamic Mode Decomposition with Control , 2014, SIAM J. Appl. Dyn. Syst..

[16]  Keisuke Fujii,et al.  Koopman Spectral Kernels for Comparing Complex Dynamics: Application to Multiagent Sport Plays , 2017, ECML/PKDD.

[17]  Yoshinobu Kawahara,et al.  Dynamic Mode Decomposition with Reproducing Kernels for Koopman Spectral Analysis , 2016, NIPS.

[18]  Yasuo Tabei,et al.  Bayesian Dynamic Mode Decomposition , 2017, IJCAI.

[19]  Bao Qi Feng,et al.  Some estimations of Banach limits , 2006 .