Rates of contraction of posterior distributions based on Gaussian process priors

A.W. Vaart, van der, J.H. Zanten, van

    Onderzoeksoutput: Bijdrage aan tijdschriftTijdschriftartikelAcademicpeer review

    151 Citaten (Scopus)
    84 Downloads (Pure)

    Samenvatting

    We derive rates of contraction of posterior distributions on nonparametric or semiparametric models based on Gaussian processes. The rate of contraction is shown to depend on the position of the true parameter relative to the reproducing kernel Hilbert space of the Gaussian process and the small ball probabilities of the Gaussian process. We determine these quantities for a range of examples of Gaussian priors and in several statistical settings. For instance, we consider the rate of contraction of the posterior distribution based on sampling from a smooth density model when the prior models the log density as a (fractionally integrated) Brownian motion. We also consider regression with Gaussian errors and smooth classification under a logistic or probit link function combined with various priors.
    Originele taal-2Engels
    Pagina's (van-tot)1435-1463
    TijdschriftThe Annals of Statistics
    Volume36
    Nummer van het tijdschrift3
    DOI's
    StatusGepubliceerd - 2008

    Vingerafdruk

    Duik in de onderzoeksthema's van 'Rates of contraction of posterior distributions based on Gaussian process priors'. Samen vormen ze een unieke vingerafdruk.

    Citeer dit