Overview Statistic: PDF-Downloads (blue) and Frontdoor-Views (gray)

Dimensionality Reduction of Complex Metastable Systems via Kernel Embeddings of Transition Manifolds

  • We present a novel kernel-based machine learning algorithm for identifying the low-dimensional geometry of the effective dynamics of high-dimensional multiscale stochastic systems. Recently, the authors developed a mathematical framework for the computation of optimal reaction coordinates of such systems that is based on learning a parameterization of a low-dimensional transition manifold in a certain function space. In this article, we enhance this approach by embedding and learning this transition manifold in a reproducing kernel Hilbert space, exploiting the favorable properties of kernel embeddings. Under mild assumptions on the kernel, the manifold structure is shown to be preserved under the embedding, and distortion bounds can be derived. This leads to a more robust and more efficient algorithm compared to the previous parameterization approaches.

Export metadata

Additional Services

Share in Twitter Search Google Scholar Statistics - number of accesses to the document
Metadaten
Author:Andreas Bittracher, Stefan Klus, Boumediene Hamzi, Christof Schütte
Document Type:Article
Parent Title (English):Journal of Nonlinear Science
Volume:31
Year of first publication:2021
DOI:https://doi.org/10.1007/s00332-020-09668-z
Accept ✔
Diese Webseite verwendet technisch erforderliche Session-Cookies. Durch die weitere Nutzung der Webseite stimmen Sie diesem zu. Unsere Datenschutzerklärung finden Sie hier.