Support vector machines for forecasting the evolution of an unknown ergodic dynamical system from observations with unknown noise

@inproceedings{Steinwart2007SupportVM,
  title={Support vector machines for forecasting the evolution of an unknown ergodic dynamical system from observations with unknown noise},
  author={Ingo Steinwart and Marian Anghel},
  year={2007}
}
  • Ingo Steinwart, Marian Anghel
  • Published 2007
  • Mathematics, Computer Science
  • We consider the problem of forecasting the next (observable) state of an unknown ergodic dynamical system from a noisy observation of the present state. Our main result shows, for example, that support vector machines (SVMs) using Gaussian RBF kernels can learn the best forecaster from a sequence of noisy observations if (a) the unknown observational noise process is bounded and has a summable α-mixing rate and (b) the unknown ergodic dynamical system is defined by a Lipschitz continuous… CONTINUE READING

    Create an AI-powered research feed to stay up to date with new papers like this posted to ArXiv

    Citations

    Publications citing this paper.
    SHOWING 1-10 OF 14 CITATIONS

    On the need for structure modelling in sequence prediction

    VIEW 7 EXCERPTS
    CITES METHODS & BACKGROUND
    HIGHLY INFLUENCED

    Embeddings and Prediction of Dynamical Time Series

    VIEW 4 EXCERPTS
    CITES BACKGROUND & METHODS
    HIGHLY INFLUENCED

    Statistical learning of kernel-based methods for non-i.i.d. observations

    VIEW 3 EXCERPTS
    CITES BACKGROUND
    HIGHLY INFLUENCED

    MACRO: A Meta-Algorithm for Conditional Risk Minimization

    VIEW 1 EXCERPT
    CITES BACKGROUND

    Kernel Density Estimation for Dynamical Systems

    VIEW 1 EXCERPT
    CITES BACKGROUND