The methods for approximation of principal points for binary distributions on the basis of submodularity

Haruka Yamashita, Hideo Suzuki

    Research output: Contribution to journalArticle

    2 Citations (Scopus)

    Abstract

    Principal points for binary distributions are able to be defined based on Flurys principal points (1990). However, finding principal points for binary distributions is hard in a straightforward manner. In this article, a method for approximating principal points for binary distributions is proposed by formulating it as an uncapacitated location problem. Moreover, it is shown that the problem of finding principal points can be solved with the aid of submodular functions. It leads to a solution whose value is at least (1 - 1/e) times the optimal value.

    Original languageEnglish
    Pages (from-to)2291-2309
    Number of pages19
    JournalCommunications in Statistics - Theory and Methods
    Volume44
    Issue number11
    DOIs
    Publication statusPublished - 2015 Jun 3

    Fingerprint

    Principal Points
    Submodularity
    Binary
    Approximation
    Submodular Function
    Location Problem

    Keywords

    • Clustering
    • Data analysis
    • Multivariate binary distribution
    • Uncapacitated location problem

    ASJC Scopus subject areas

    • Statistics and Probability

    Cite this

    The methods for approximation of principal points for binary distributions on the basis of submodularity. / Yamashita, Haruka; Suzuki, Hideo.

    In: Communications in Statistics - Theory and Methods, Vol. 44, No. 11, 03.06.2015, p. 2291-2309.

    Research output: Contribution to journalArticle

    @article{70e7824eaea4432fa47dec642cbc55f3,
    title = "The methods for approximation of principal points for binary distributions on the basis of submodularity",
    abstract = "Principal points for binary distributions are able to be defined based on Flurys principal points (1990). However, finding principal points for binary distributions is hard in a straightforward manner. In this article, a method for approximating principal points for binary distributions is proposed by formulating it as an uncapacitated location problem. Moreover, it is shown that the problem of finding principal points can be solved with the aid of submodular functions. It leads to a solution whose value is at least (1 - 1/e) times the optimal value.",
    keywords = "Clustering, Data analysis, Multivariate binary distribution, Uncapacitated location problem",
    author = "Haruka Yamashita and Hideo Suzuki",
    year = "2015",
    month = "6",
    day = "3",
    doi = "10.1080/03610926.2013.781645",
    language = "English",
    volume = "44",
    pages = "2291--2309",
    journal = "Communications in Statistics - Theory and Methods",
    issn = "0361-0926",
    publisher = "Taylor and Francis Ltd.",
    number = "11",

    }

    TY - JOUR

    T1 - The methods for approximation of principal points for binary distributions on the basis of submodularity

    AU - Yamashita, Haruka

    AU - Suzuki, Hideo

    PY - 2015/6/3

    Y1 - 2015/6/3

    N2 - Principal points for binary distributions are able to be defined based on Flurys principal points (1990). However, finding principal points for binary distributions is hard in a straightforward manner. In this article, a method for approximating principal points for binary distributions is proposed by formulating it as an uncapacitated location problem. Moreover, it is shown that the problem of finding principal points can be solved with the aid of submodular functions. It leads to a solution whose value is at least (1 - 1/e) times the optimal value.

    AB - Principal points for binary distributions are able to be defined based on Flurys principal points (1990). However, finding principal points for binary distributions is hard in a straightforward manner. In this article, a method for approximating principal points for binary distributions is proposed by formulating it as an uncapacitated location problem. Moreover, it is shown that the problem of finding principal points can be solved with the aid of submodular functions. It leads to a solution whose value is at least (1 - 1/e) times the optimal value.

    KW - Clustering

    KW - Data analysis

    KW - Multivariate binary distribution

    KW - Uncapacitated location problem

    UR - http://www.scopus.com/inward/record.url?scp=84933074037&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=84933074037&partnerID=8YFLogxK

    U2 - 10.1080/03610926.2013.781645

    DO - 10.1080/03610926.2013.781645

    M3 - Article

    VL - 44

    SP - 2291

    EP - 2309

    JO - Communications in Statistics - Theory and Methods

    JF - Communications in Statistics - Theory and Methods

    SN - 0361-0926

    IS - 11

    ER -