Elicitation and identification of properties

Ingo Steinwart, Chloé Pasin, Robert C. Williamson, Siyu Zhang

    Research output: Contribution to journalConference articlepeer-review

    44 Citations (Scopus)

    Abstract

    Properties of distributions are real-valued functionals such as the mean, quantile or conditional value at risk. A property is elicitable if there exists a scoring function such that minimization of the associated risks recovers the property. We extend existing results to characterize the elicitability of properties in a general setting. We further relate elicitability to identifiability (a notion introduced by Osband) and provide a general formula describing all scoring functions for an elicitable property. Finally, we draw some connections to the theory of coherent risk measures.

    Original languageEnglish
    Pages (from-to)482-526
    Number of pages45
    JournalJournal of Machine Learning Research
    Volume35
    Publication statusPublished - 2014
    Event27th Conference on Learning Theory, COLT 2014 - Barcelona, Spain
    Duration: 13 Jun 201415 Jun 2014

    Fingerprint

    Dive into the research topics of 'Elicitation and identification of properties'. Together they form a unique fingerprint.

    Cite this