Corpus ID: 16557391

On Optimal Global Rates Of Convergence For Nonparametric Regression With Random Design

@inproceedings{Kohler2000OnOG,
  title={On Optimal Global Rates Of Convergence For Nonparametric Regression With Random Design},
  author={Michael Kohler},
  year={2000}
}
  • Michael Kohler
  • Published 2000
  • Mathematics
  • Estimation of univariate regression functions from bounded i.i.d. data is considered. The L 2 {error with integration with respect to the design measure is used as an error criterion. The aim of this paper is to show that it is possible to achieve for k{smooth regression functions the well{known optimal global rate of convergence n ? 2k 2k+1 without assuming anything on the underlying distribution besides boundedness and without knowing the smoothness of the regression function in advance. The… CONTINUE READING

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

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 40 REFERENCES

    Estimating a regression function

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    A Probabilistic Theory of Pattern Recognition

    VIEW 5 EXCERPTS
    HIGHLY INFLUENTIAL

    Model selection for regression on random design. Submitted for publication

    • Y. Baraud
    • 1997
    VIEW 3 EXCERPTS
    HIGHLY INFLUENTIAL

    On the universal consistency of a least squares spline regression estimator

    • M. Kohler
    • Math. Methods of Statistics
    • 1997
    VIEW 3 EXCERPTS
    HIGHLY INFLUENTIAL

    Strong universal consistency of kernel and partitioning regressionestimates

    • H. Walk
    • Preprint
    • 1997
    VIEW 1 EXCERPT
    HIGHLY INFLUENTIAL

    On the strong universal consistency of nearest neighbor regression function estimates

    • L. Devroye, L. Gyor, A. Krzy zak, G. Lugosi
    • Ann. Statist
    • 1994
    VIEW 3 EXCERPTS
    HIGHLY INFLUENTIAL

    Regression analysis and empirical processes

    VIEW 1 EXCERPT
    HIGHLY INFLUENTIAL