Repository: Freie Universit├Ąt Berlin, Math Department

Eigendecompositions of Transfer Operators in Reproducing Kernel Hilbert Spaces

Klus, S. and Schuster, I. and Muandet, K. (2017) Eigendecompositions of Transfer Operators in Reproducing Kernel Hilbert Spaces. SFB 1114 Preprint in SciRate arXiv:1712.01572 . pp. 1-33. (Unpublished)

[img]
Preview
PDF
1MB

Official URL: https://scirate.com/arxiv/1712.01572

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 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 in the machine learning community. Moreover, numerical methods to compute empirical estimates of these embeddings are akin to data-driven methods for the approximation of transfer operators such as extended dynamic mode decomposition and its variants. In fact, most of the existing methods can be derived from our framework, providing a unifying view on the approximation of transfer operators. One main benefit of the presented kernel-based approaches is that these methods can be applied to any domain where a similarity measure given by a kernel is available. 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.

Item Type:Article
Subjects:Mathematical and Computer Sciences > Mathematics > Applied Mathematics
ID Code:2163
Deposited By: Silvia Hoemke
Deposited On:13 Dec 2017 09:35
Last Modified:13 Dec 2017 09:35

Repository Staff Only: item control page