Efficient approximation of molecular kinetics using random Fourier features

Feliks Nüske, Stefan Klus

Research output: Contribution to journalArticlepeer-review

27 Downloads (Pure)


Slow kinetic processes in molecular systems can be analyzed by computing the dominant eigenpairs of the Koopman operator or its generator. In this context, the Variational Approach to Markov Processes (VAMP) provides a rigorous way of discerning the quality of different approximate models. Kernel methods have been shown to provide accurate and robust estimates for slow kinetic processes, but they are sensitive to hyper-parameter selection and require the solution of large-scale generalized eigenvalue problems, which can easily become computationally demanding for large data sizes. In this contribution, we employ a stochastic approximation of the kernel based on random Fourier features (RFFs) to derive a small-scale dual eigenvalue problem that can be easily solved. We provide an interpretation of this procedure in terms of a finite, randomly generated basis set. By combining the RFF approach and model selection by means of the VAMP score, we show that kernel parameters can be efficiently tuned and accurate estimates of slow molecular kinetics can be obtained for several benchmarking systems, such as deca alanine and the NTL9 protein.

Original languageEnglish
Article number074105
JournalThe Journal of Chemical Physics
Issue number7
Early online date18 Aug 2023
Publication statusPublished - 21 Aug 2023

ASJC Scopus subject areas

  • Physics and Astronomy(all)
  • Physical and Theoretical Chemistry


Dive into the research topics of 'Efficient approximation of molecular kinetics using random Fourier features'. Together they form a unique fingerprint.

Cite this