iterLap (Q153490)

From MaRDI portal





Approximate Probability Densities by Iterated Laplace Approximations
Language Label Description Also known as
English
iterLap
Approximate Probability Densities by Iterated Laplace Approximations

    Statements

    0 references
    1.1-3
    5 August 2017
    0 references
    1.0-1
    9 March 2011
    0 references
    1.0-2
    23 October 2011
    0 references
    1.1-1
    13 November 2011
    0 references
    1.1-2
    22 May 2012
    0 references
    1.1-4
    30 September 2023
    0 references
    0 references
    30 September 2023
    0 references
    The iterLap (iterated Laplace approximation) algorithm approximates a general (possibly non-normalized) probability density on R^p, by repeated Laplace approximations to the difference between current approximation and true density (on log scale). The final approximation is a mixture of multivariate normal distributions and might be used for example as a proposal distribution for importance sampling (eg in Bayesian applications). The algorithm can be seen as a computational generalization of the Laplace approximation suitable for skew or multimodal densities.
    0 references
    0 references
    0 references
    0 references
    0 references
    0 references

    Identifiers

    0 references