Concentration estimates for learning with unbounded sampling (Q1946480)

From MaRDI portal
scientific article
Language Label Description Also known as
English
Concentration estimates for learning with unbounded sampling
scientific article

    Statements

    Concentration estimates for learning with unbounded sampling (English)
    0 references
    0 references
    0 references
    15 April 2013
    0 references
    Kernel based least square regression learning with unbounded sampling processes is studied. By a moment hypothesis for unbounded sampling, an approximation assumption for the regression function, and capacity condition for hypothesis space, sharper learning rates are derived. In the error analysis, a probability inequality for unbounded random variables is introduced, and an iteration technique is used.
    0 references
    0 references
    learning theory
    0 references
    least-square regression
    0 references
    regularization in reproducing kernel Hilbert spaces
    0 references
    empirical covering number
    0 references
    concentration estimates
    0 references
    0 references
    0 references

    Identifiers