Enregistré dans:
Détails bibliographiques
Auteurs principaux: Grigoryeva, Lyudmila, Louw, James, Ortega, Juan-Pablo
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:https://arxiv.org/abs/2405.02536
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866913746259017728
author Grigoryeva, Lyudmila
Louw, James
Ortega, Juan-Pablo
author_facet Grigoryeva, Lyudmila
Louw, James
Ortega, Juan-Pablo
contents An iterated multistep forecasting scheme based on recurrent neural networks (RNN) is proposed for the time series generated by causal chains with infinite memory. This forecasting strategy contains, as a particular case, the iterative prediction strategies for dynamical systems that are customary in reservoir computing. Explicit error bounds are obtained as a function of the forecasting horizon, functional and dynamical features of the specific RNN used, and the approximation error committed by it. In particular, the growth rate of the error is shown to be exponential and controlled by the top Lyapunov exponent of the proxy system. The framework in the paper circumvents difficult-to-verify embedding hypotheses that appear in previous references in the literature and applies to new situations like the finite-dimensional observations of functional differential equations or the deterministic parts of stochastic processes to which standard embedding techniques do not necessarily apply.
format Preprint
id arxiv_https___arxiv_org_abs_2405_02536
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Forecasting causal dynamics with universal reservoirs
Grigoryeva, Lyudmila
Louw, James
Ortega, Juan-Pablo
Dynamical Systems
An iterated multistep forecasting scheme based on recurrent neural networks (RNN) is proposed for the time series generated by causal chains with infinite memory. This forecasting strategy contains, as a particular case, the iterative prediction strategies for dynamical systems that are customary in reservoir computing. Explicit error bounds are obtained as a function of the forecasting horizon, functional and dynamical features of the specific RNN used, and the approximation error committed by it. In particular, the growth rate of the error is shown to be exponential and controlled by the top Lyapunov exponent of the proxy system. The framework in the paper circumvents difficult-to-verify embedding hypotheses that appear in previous references in the literature and applies to new situations like the finite-dimensional observations of functional differential equations or the deterministic parts of stochastic processes to which standard embedding techniques do not necessarily apply.
title Forecasting causal dynamics with universal reservoirs
topic Dynamical Systems
url https://arxiv.org/abs/2405.02536