Robust reductions from ranking to classification

M.F. Balcan, N. Bansal, A. Beygelzimer, D. Coppersmith, J. Langford, G.B. Sorkin

    Onderzoeksoutput: Hoofdstuk in Boek/Rapport/CongresprocedureConferentiebijdrageAcademicpeer review

    16 Citaten (Scopus)


    We reduce ranking, as measured by the Area Under the Receiver Operating Characteristic Curve (AUC), to binary classification. The core theorem shows that a binary classification regret of r on the induced binary problem implies an AUC regret of at most 2r. This is a large improvement over approaches such as ordering according to regressed scores, which have a regret transform of $r \mapsto nr$ where n is the number of elements.
    Originele taal-2Engels
    TitelLearning theory (20th Annual Conference, COLT 2007, San Diego CA, USA, June 13–15, 2007. Proceedings)
    RedacteurenN.H. Bshouty, C. Gentile
    Plaats van productieBerlin
    ISBN van geprinte versie978-3-540-72925-9
    StatusGepubliceerd - 2007

    Publicatie series

    NaamLecture Notes in Computer Science
    ISSN van geprinte versie0302-9743


    Duik in de onderzoeksthema's van 'Robust reductions from ranking to classification'. Samen vormen ze een unieke vingerafdruk.

    Citeer dit