A mathematical framework for time-delay reservoir computing analysis

• URL: http://arxiv.org/abs/2603.18706v1
• Date: Thu, 19 Mar 2026 10:05:31 GMT
• Title: A mathematical framework for time-delay reservoir computing analysis
• Abstract summary: Reservoir computing is a well-established approach for processing data with a much lower complexity than neural networks.<n>Despite two decades of experimental progress, the core properties of reservoir computing still lack rigorous mathematical foundations.<n>This paper addresses this gap by providing a control-theoretic framework for the analysis of time-delay-based reservoir computers.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Reservoir computing is a well-established approach for processing data with a much lower complexity compared to traditional neural networks. Despite two decades of experimental progress, the core properties of reservoir computing (namely separation, robustness, and fading memory) still lack rigorous mathematical foundations. This paper addresses this gap by providing a control-theoretic framework for the analysis of time-delay-based reservoir computers. We introduce formal definitions of the separation property and fading memory in terms of functional norms, and establish their connection to well-known stability notions for time-delay systems as incremental input-to-state stability. For a class of linear reservoirs, we derive an explicit lower bound for the separation distance via Fourier analysis, offering a computable criterion for reservoir design. Numerical results on the NARMA10 benchmark and continuous-time system prediction validate the approach with a minimal digital implementation.

Related papers

• Anticipating tipping in spatiotemporal systems with machine learning [0.0]
  We use a machine-learning framework of parameter-adaptable reservoir computing to accurately anticipate tipping in complex dynamical systems.<n>We demonstrate tipping can be identified within a prediction window across a variety of timetemporal dynamical systems, as well as in CMIP5Coupled Model Intercomparison Project 5 climate.
  arXiv  Detail & Related papers  (2026-04-07T20:51:58Z)
• A Programmable Linear Optical Quantum Reservoir with Measurement Feedback for Time Series Analysis [0.0]
  We investigate a linear-optical quantum reservoir architecture for time-series processing based on multiphoton interference.<n>By sweeping the feedback strength, we identify three dynamical regimes and find that memory performance peaks near the stability boundary.<n>The proposed architecture is compatible with current photonic technology and lowers the experimental barrier to feedback-driven QRC for time-series analysis.
  arXiv  Detail & Related papers  (2026-02-19T15:08:32Z)
• Next-Generation Reservoir Computing for Dynamical Inference [0.0]
  We present a simple and scalable implementation of next-generation reservoir computing for modeling dynamical systems from time series data.<n>Our approach uses a pseudorandom nonlinear projection of time-delay embedded, allowing an arbitrary dimension of the feature space.<n>We apply the method to benchmark tasks -- including attractor reconstruction and bifurcation diagram estimation -- using only partial and noisy observations.
  arXiv  Detail & Related papers  (2025-09-14T16:28:48Z)
• Multivariate Long-term Time Series Forecasting with Fourier Neural Filter [42.60778405812048]
  We introduce FNF as the backbone and DBD as architecture to provide excellent learning capabilities and optimal learning pathways for spatial-temporal modeling.<n>We show that FNF unifies local time-domain and global frequency-domain information processing within a single backbone that extends naturally to spatial modeling.
  arXiv  Detail & Related papers  (2025-06-10T18:40:20Z)
• Scalable Signature Kernel Computations for Long Time Series via Local Neumann Series Expansions [46.685771141109306]
  The signature kernel is a recent state-of-the-art tool for analyzing high-dimensional sequential data.<n>We present a novel method for efficiently computing the signature kernel of long, high-dimensional time series.<n>This method achieves substantial performance improvements over state-of-the-art approaches for computing the signature kernel.
  arXiv  Detail & Related papers  (2025-02-27T18:59:20Z)
• MultiPDENet: PDE-embedded Learning with Multi-time-stepping for Accelerated Flow Simulation [48.41289705783405]
  We propose a PDE-embedded network with multiscale time stepping (MultiPDENet)<n>In particular, we design a convolutional filter based on the structure of finite difference with a small number of parameters to optimize.<n>A Physics Block with a 4th-order Runge-Kutta integrator at the fine time scale is established that embeds the structure of PDEs to guide the prediction.
  arXiv  Detail & Related papers  (2025-01-27T12:15:51Z)
• Deep End-to-End Survival Analysis with Temporal Consistency [49.77103348208835]
  We present a novel Survival Analysis algorithm designed to efficiently handle large-scale longitudinal data. A central idea in our method is temporal consistency, a hypothesis that past and future outcomes in the data evolve smoothly over time. Our framework uniquely incorporates temporal consistency into large datasets by providing a stable training signal.
  arXiv  Detail & Related papers  (2024-10-09T11:37:09Z)
• Oscillations enhance time-series prediction in reservoir computing with feedback [3.3686252536891454]
  Reservoir computing is a machine learning framework used for modeling the brain. It is difficult to accurately reproduce the long-term target time series because the reservoir system becomes unstable. This study proposes oscillation-driven reservoir computing (ODRC) with feedback.
  arXiv  Detail & Related papers  (2024-06-05T02:30:29Z)
• Reservoir Computing with Generalized Readout based on Generalized Synchronization [0.0]
  Reservoir computing is a machine learning framework that exploits nonlinear dynamics. We propose a novel reservoir computing framework with generalized readout, including a nonlinear combination of reservoir variables. In a numerical study, we find that introducing the generalized readout leads to a significant improvement in accuracy and an unexpected enhancement in robustness.
  arXiv  Detail & Related papers  (2024-05-03T10:03:59Z)
• Effect of temporal resolution on the reproduction of chaotic dynamics via reservoir computing [0.0]
  Reservoir computing is a machine learning paradigm that uses a structure called a reservoir, which has nonlinearities and short-term memory. This study analyzes the effect of sampling on the ability of reservoir computing to autonomously regenerate chaotic time series.
  arXiv  Detail & Related papers  (2023-01-27T13:31:15Z)
• A Constraint-Based Algorithm for the Structural Learning of Continuous-Time Bayesian Networks [70.88503833248159]
  We propose the first constraint-based algorithm for learning the structure of continuous-time Bayesian networks. We discuss the different statistical tests and the underlying hypotheses used by our proposal to establish conditional independence.
  arXiv  Detail & Related papers  (2020-07-07T07:34:09Z)
• Supporting Optimal Phase Space Reconstructions Using Neural Network Architecture for Time Series Modeling [68.8204255655161]
  We propose an artificial neural network with a mechanism to implicitly learn the phase spaces properties. Our approach is either as competitive as or better than most state-of-the-art strategies.
  arXiv  Detail & Related papers  (2020-06-19T21:04:47Z)
• On dissipative symplectic integration with applications to gradient-based optimization [77.34726150561087]
  We propose a geometric framework in which discretizations can be realized systematically. We show that a generalization of symplectic to nonconservative and in particular dissipative Hamiltonian systems is able to preserve rates of convergence up to a controlled error.
  arXiv  Detail & Related papers  (2020-04-15T00:36:49Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.