cs.LGSep 24, 2025

How deep is your network? Deep vs. shallow learning of transfer operators

Authors: Mohammad Tabish, Benedict Leimkuhler, Stefan Klus

Organizations: Maxwell Institute for Mathematical Sciences, University of Edinburgh and Heriot–Watt University, Edinburgh, UK · School of Mathematics, University of Edinburgh, Edinburgh, UK · School of Mathematical and Computer Sciences, Heriot–Watt University, Edinburgh, UK

Abstract

We introduce RaNNDy, a randomized neural network framework for learning transfer operators and their spectral decompositions. By fixing the weights of the hidden layers and training only the output layer, RaNNDy achieves significant reductions in computational costs -- often by two orders of magnitude -- with similar accuracy compared to state-of-the-art deep learning methods. The method is less sensitive to hyperparameter tuning and provides a closed-form solution for the output layer weights that directly represent eigenfunctions of the learned operator. Moreover, it is possible to estimate uncertainties associated with the computed spectral properties via ensemble learning. We demonstrate the efficacy of the proposed approach using diverse benchmark problems, including stochastic dynamical systems and protein folding processes, highlighting the strengths but also weaknesses of RaNNDy.

Figures & tables

Appendix figures & tables12 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Optimization of randomized neural networks for transfer operator approximation

    May 22, 2026Mohammad Tabish, Stefan KlusDynamical SystemsNeural Network Optimization

  2. Randomized neural operator for parametric PDEs with fast training and conformal uncertainty quantification

    Jun 28, 2026Zirui Deng, Jingbo Sun, Deyu Meng +1Uncertainty QuantificationPDE Surrogate Modeling

  3. Randomized Neural Networks for Integro-Differential Equations with Application to Neutron Transport

    Apr 15, 2026Haoning Dang, Fei Wang, Yifan Chen +3Neural PDE Solvers