Sparse density estimator with tunable kernels

Xia Hong, Sheng Chen, Victor Becerra

    Research output: Contribution to journalArticlepeer-review

    98 Downloads (Pure)

    Abstract

    A new sparse kernel density estimator with tunable kernels is introduced within a forward constrained regression framework whereby the nonnegative and summing-to-unity constraints of the mixing weights can easily be satisfied. Based on the minimum integrated square error criterion, a recursive algorithm is developed to select significant kernels one at time, and the kernel width of the selected kernel is then tuned using the gradient descent algorithm. Numerical examples are employed to demonstrate that the proposed approach is effective in constructing very sparse kernel density estimators with competitive accuracy to existing kernel density estimators.
    Original languageEnglish
    Pages (from-to)1976–1982
    Number of pages7
    JournalNeurocomputing
    Volume173
    Issue number3
    DOIs
    Publication statusPublished - 15 Jan 2016

    Keywords

    • Probability density function
    • Kernel density estimator
    • Sparse modeling
    • Minimum integrated square error

    Fingerprint

    Dive into the research topics of 'Sparse density estimator with tunable kernels'. Together they form a unique fingerprint.

    Cite this