mlsanityData to 7 Oct 2026

Deep Koopman-layered Model with Universal Property Based on Toeplitz Matrices

arXiv 2410.02199 ↗First posted 3 Oct 2024cs.LG math.DS math.FAcited by 0

Not on the map. Why?

Abstract (arXiv)

We propose deep Koopman-layered models with learnable parameters in the form of Toeplitz matrices for analyzing the transition of the dynamics of time-series data. The proposed model has both theoretical solidness and flexibility. By virtue of the universal property of Toeplitz matrices and the reproducing property underlying the model, we show its universality and generalization property. In addition, the flexibility of the proposed model enables the model to fit time-series data coming from nonautonomous dynamical systems. When training the model, we apply Krylov subspace methods for efficient computations, which establish a new connection between Koopman operators and numerical linear algebra. We also empirically demonstrate that the proposed model outperforms existing methods on eigenvalue estimation of multiple Koopman operators for nonautonomous systems.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 28 of its 59 references that are in the map. First posted on arXiv 3 Oct 2024.

Builds on

28 of 59 references.

References · 28

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2018Neural Ordinary Differential Equationscited by 3,733
  3. 2021Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecastingcited by 1,654
  4. 2017Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networkscited by 869
  5. 2017Spectrally-normalized margin bounds for neural networkscited by 681
  6. 2017Deep learning for universal linear embeddings of nonlinear dynamicscited by 491
  7. 2015Norm-Based Capacity Control in Neural Networkscited by 299
  8. 2017Size-Independent Sample Complexity of Neural Networkscited by 289
  9. 2017VAMPnets: Deep learning of molecular kineticscited by 135
  10. 2020Forecasting Sequential Data using Consistent Koopman Autoencoderscited by 114
  11. 2023Koopa: Learning Non-stationary Time Series Dynamics with Koopman Predictorscited by 110
  12. 2020Coupling-based Invertible Neural Networks Are Universal Diffeomorphism Approximatorscited by 85
16 more
  1. 2019Deep Learning via Dynamical Systems: An Approximation Perspectivecited by 78
  2. 2017Eigendecompositions of Transfer Operators in Reproducing Kernel Hilbert Spacescited by 48
  3. 2021Rigorous data-driven computation of spectral properties of Koopman operators for dynamical systemscited by 44
  4. 2020Universal Approximation Property of Neural Ordinary Differential Equationscited by 32
  5. 2017Koopman operator-based model reduction for switched-system control of PDEscited by 31
  6. 2020Kernel-based approximation of the Koopman generator and Schr"odinger operatorcited by 31
  7. 2023Koopman neural operator as a mesh-free solver of non-linear partial differential equationscited by 29
  8. 2022Deep Koopman Operator with Control for Nonlinear Systemscited by 25
  9. 2023Koopman Kernel Regressioncited by 22
  10. 2022The mpEDMD Algorithm for Data-Driven Computations of Measure-Preserving Dynamical Systemscited by 21
  11. 2023Koopman-based generalization bound: New aspect for full-rank weightscited by 9
  12. 2024Koopman operators with intrinsic observables in rigged reproducing kernel Hilbert spacescited by 9
  13. 2018Metric on Nonlinear Dynamical Systems with Perron-Frobenius Operatorscited by 7
  14. 2019Krylov Subspace Method for Nonlinear Dynamical Systems with Random Noisecited by 7
  15. 2022Stable Invariant Models via Koopman Spectracited by 4
  16. 2024Forward-Backward Extended DMD with an Asymptotic Stability Constraintcited by 3

Built on by

Not cited yet.