Supervised Learning of Lyapunov Functions Using Laplace Averages of Approximate Koopman Eigenfunctions

Shankar A. Deka, Dimos V. Dimarogonas

Research output: Contribution to journalArticleScientificpeer-review


Modern data-driven techniques have rapidly progressed beyond modelling and systems identification, with a growing interest in learning high-level dynamical properties of a system, such as safe-set invariance, reachability, input-to-state stability etc. In this letter, we propose a novel supervised Deep Learning technique for constructing Lyapunov certificates, by leveraging Koopman Operator theory-based numerical tools (Extended Dynamic Mode Decomposition and Generalized Laplace Analysis) to robustly and efficiently generate explicit ground truth data for training. This is in stark contrast to existing Deep Learning methods where the loss functions plainly penalize Lyapunov condition violation in the absence of labelled data for direct regression. Furthermore, our approach leads to a linear parameterization of Lyapunov candidate functions in terms of stable eigenfunctions of the Koopman operator, making them more interpretable compared to standard DNN-based architecture. We demonstrate and validate our approach numerically using 2-dimensional and 10-dimensional examples.
Original languageEnglish
Article number10171181
Pages (from-to)3072-3077
Number of pages6
JournalIEEE Control Systems Letters
Publication statusPublished - 1 Jan 2023
MoE publication typeA1 Journal article-refereed


  • Eigenvalues and eigenfunctions
  • Lyapunov methods
  • Trajectory
  • Convergence
  • Deep learning
  • Neural networks
  • Stability analysis


Dive into the research topics of 'Supervised Learning of Lyapunov Functions Using Laplace Averages of Approximate Koopman Eigenfunctions'. Together they form a unique fingerprint.

Cite this