Skip to main navigation Skip to search Skip to main content

Fat-Shattering Dimension of k-fold Aggregations

    Research output: Contribution to journal › Article › peer-review

    4 Scopus citations

    Abstract

    We provide estimates on the fat-shattering dimension of aggregation rules of real-valued function classes. The latter consists of all ways of choosing k functions, one from each of the k classes, and computing pointwise an “aggregate” function of these, such as the median, mean, and maximum. The bounds are stated in terms of the fat-shattering dimensions of the component classes. For linear and affine function classes, we provide a considerably sharper upper bound and a matching lower bound, achieving, in particular, an optimal dependence on k. Along the way, we improve several known results in addition to pointing out and correcting a number of erroneous claims in the literature.

    Original languageEnglish
    JournalJournal of Machine Learning Research
    Volume25
    StatePublished - 1 Jan 2024

    Keywords

    • aggregation rules
    • combinatorial dimension
    • ensemble methods
    • fat-shattering dimension
    • k-fold maximum
    • scale-sensitive dimension

    ASJC Scopus subject areas

    • Software
    • Control and Systems Engineering
    • Statistics and Probability
    • Artificial Intelligence

    Fingerprint

    Dive into the research topics of 'Fat-Shattering Dimension of k-fold Aggregations'. Together they form a unique fingerprint.

    Cite this