mlsanityData to 14 Oct 2026

A finite-sample generalization bound for stable LPV systems

arXiv 2405.10054 ↗First posted 16 May 2024cs.LG cs.SY eess.SYcited by 0

Not on the map. Why?

Abstract (arXiv)

One of the main theoretical challenges in learning dynamical systems from data is providing upper bounds on the generalization error, that is, the difference between the expected prediction error and the empirical prediction error measured on some finite sample. In machine learning, a popular class of such bounds are the so-called Probably Approximately Correct (PAC) bounds. In this paper, we derive a PAC bound for stable continuous-time linear parameter-varying (LPV) systems. Our bound depends on the H2 norm of the chosen class of the LPV systems, but does not depend on the time interval for which the signals are considered.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 28 of its 82 references that are in the map. First posted on arXiv 16 May 2024.

Builds on

28 of 82 references.

References · 28

  1. 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,718
  2. 2018Neural Ordinary Differential Equationscited by 3,779
  3. 2021Combining Recurrent, Convolutional, and Continuous-time Models with Linear State-Space Layerscited by 608
  4. 2023Resurrecting Recurrent Neural Networks for Long Sequencescited by 408
  5. 2022On Neural Differential Equationscited by 268
  6. 2021User-friendly introduction to PAC-Bayes boundscited by 239
  7. 2020Dissecting Neural ODEscited by 153
  8. 2022How to Train Your HiPPO: State Space Models with Generalized Orthogonal Basis Projectionscited by 122
  9. 2018Echo state networks are universalcited by 87
  10. 2019Data-dependent Sample Complexity of Deep Neural Networks via Lipschitz Augmentationcited by 71
  11. 2019Finite Sample Analysis of Stochastic System Identificationcited by 67
  12. 2019Learning Linear Dynamical Systems with Semi-Parametric Least Squarescited by 58
16 more
  1. 2022Statistical Learning Theory for Control: A Finite Sample Perspectivecited by 53
  2. 2019On Generalization Bounds of a Family of Recurrent Neural Networkscited by 42
  3. 2020Logarithmic Regret for Adversarial Online Controlcited by 41
  4. 2017Universal discrete-time reservoir computers with stochastic inputs and linear readouts using non-homogeneous state-affine systemscited by 39
  5. 2023State-space Models with Layer-wise Nonlinearity are Universal Approximators with Exponential Decaying Memorycited by 39
  6. 2020Non-asymptotic Identification of Linear Dynamical Systems Using Multiple Trajectoriescited by 38
  7. 2020On the Curse of Memory in Recurrent Neural Networks: Approximation and Optimization Analysiscited by 27
  8. 2021Framing RNN as a kernel method: A neural ODE approachcited by 23
  9. 2023Generalization bounds for neural ordinary differential equations and deep residual networkscited by 21
  10. 2020Learning Recurrent Neural Net Models of Nonlinear Systemscited by 11
  11. 2024Rademacher Complexity of Neural ODEs via Chen-Fliess Seriescited by 5
  12. 2023PAC-Bayesian bounds for learning LTI-ss systems with input from empirical losscited by 4
  13. 2023PAC-Bayes Generalisation Bounds for Dynamical Systems Including Stable RNNscited by 4
  14. 2021Reduced-order modeling of LPV systems in the Loewner frameworkcited by 3
  15. 2021LPVcore: MATLAB Toolbox for LPV Modelling, Identification and Controlcited by 3
  16. 2018Towards Efficient Maximum Likelihood Estimation of LPV-SS Modelscited by 2

Built on by

Not cited yet.