• DocumentCode
    847742
  • Title

    Correction to "The Importance of Convexity in Learning With Squared Loss" [Sep 98 1974-1980]

  • Author

    Wee Sun Lee ; Bartlett, P.L. ; Williamson, R.C.

  • Author_Institution
    Dept. of Comput. Sci., Nat. Univ. of Singapore, Singapore
  • Volume
    54
  • Issue
    9
  • fYear
    2008
  • Firstpage
    4395
  • Lastpage
    4395
  • Abstract
    The paper "the importance of convexity in learning with squared loss" gave a lower bound on the sample complexity of learning with quadratic loss using a nonconvex function class. The proof contains an error. We show that the lower bound is true under a stronger condition that holds for many cases of interest.
  • Keywords
    computational complexity; learning (artificial intelligence); convexity importance; nonconvex function class; quadratic loss; sample complexity; squared loss; Algorithm design and analysis; Australia; Computer science; Hilbert space; Minimization methods; Pattern recognition; Probability distribution; Statistical learning; Statistics; Sun; Agnostic learning; lower bound; sample complexity;
  • fLanguage
    English
  • Journal_Title
    Information Theory, IEEE Transactions on
  • Publisher
    ieee
  • ISSN
    0018-9448
  • Type

    jour

  • DOI
    10.1109/TIT.2008.928242
  • Filename
    4608980
    • Link To Document
    https://search.isc.ac/dl/search/defaultta.aspx?DTC=49&DC=847742