• DocumentCode
    771647
  • Title

    Improving the sample complexity using global data

  • Author

    Mendelson, Shahar

  • Author_Institution
    Comput. Sci. Lab., Australian Nat. Univ., Canberra, ACT, Australia
  • Volume
    48
  • Issue
    7
  • fYear
    2002
  • fDate
    7/1/2002 12:00:00 AM
  • Firstpage
    1977
  • Lastpage
    1991
  • Abstract
    We study the sample complexity of proper and improper learning problems with respect to different q-loss functions. We improve the known estimates for classes which have relatively small covering numbers in empirical L2 spaces (e.g. log-covering numbers which are polynomial with exponent p<2). We present several examples of relevant classes which have a "small" fat-shattering dimension, and hence fit our setup, the most important of which are kernel machines
  • Keywords
    communication complexity; estimation theory; functions; information theory; learning (artificial intelligence); losses; polynomials; signal sampling; Glivenko-Cantelli classes; fat-shattering dimension; global data; improper learning problems; kernel machines; log-covering numbers; polynomial; proper learning problems; q-loss functions; sample complexity; small covering numbers; uniform convexity; Australia; Convergence; Extraterrestrial measurements; Kernel; Machine learning; Neural networks; Polynomials; Random variables; Statistics;
  • fLanguage
    English
  • Journal_Title
    Information Theory, IEEE Transactions on
  • Publisher
    ieee
  • ISSN
    0018-9448
  • Type

    jour

  • DOI
    10.1109/TIT.2002.1013137
  • Filename
    1013137
    • Link To Document
    https://search.isc.ac/dl/search/defaultta.aspx?DTC=49&DC=771647