Indefinite Kernel Discriminant Analysis (invited paper)

B. Haasdonk, E. Pekalska

    Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

    Abstract

    Kernel methods for data analysis are frequently considered to be restricted to positive definite kernels. In practice, however, indefinite kernels arise e.g. from problem-specific kernel construction or optimized similarity measures. We, therefore, present formal extensions of some kernel discriminant analysis methods which can be used with indefinite kernels. In particular these are the multi-class kernel Fisher discriminant and the kernel Mahalanobis distance. The approaches are empirically evaluated in classification scenarios on indefinite multi-class datasets.
    Original languageEnglish
    Title of host publicationhost publication
    Pages221-230
    Number of pages10
    Publication statusPublished - 2010
    EventInternational Conference on Computational Statistics -
    Duration: 1 Jan 1824 → …

    Conference

    ConferenceInternational Conference on Computational Statistics
    Period1/01/24 → …

    Keywords

    • Kernel Methods, Indefinite Kernels, Mahalanobis Distance, Fisher Discriminant Analysis

    Fingerprint

    Dive into the research topics of 'Indefinite Kernel Discriminant Analysis (invited paper)'. Together they form a unique fingerprint.

    Cite this