An inequality for uniform deviations of sample averages from their means (Q1962162): Difference between revisions

From MaRDI portal
RedirectionBot (talk | contribs)
Removed claim: author (P16): Item:Q162843
RedirectionBot (talk | contribs)
Changed an Item
Property / author
 
Property / author: Bartlett, Peter L. / rank
 
Normal rank

Revision as of 23:28, 9 February 2024

scientific article
Language Label Description Also known as
English
An inequality for uniform deviations of sample averages from their means
scientific article

    Statements

    An inequality for uniform deviations of sample averages from their means (English)
    0 references
    0 references
    0 references
    12 December 2001
    0 references
    Let \(X_1,\dots,X_n\) be independent and identically distributed random variables with values in some arbitrary set \(\mathcal{X}\), and let \(\mathcal{F}\) be a class of uniformly bounded functions from \(\mathcal{X}\) to \([0,1]\). For \(f\in\mathcal{F}\), introduce the sample averages \(P_n(f)=n^{-1}\sum_{i=1}^nf(X_i)\) and the population means \(P(f)=E(f(X_1))\). The authors derive new exponential bounds on \[ P(\sup_{f\in\mathcal{F}}(P(f)-P_n(f)-\gamma)/\sqrt{P(f)}>\varepsilon) \] and \[ P(\sup_{f\in\mathcal{F}}(P_n(f)-P(f)-\gamma)/\sqrt{P_n(f)}>\varepsilon) \] which involve an appropriate expected coverage number to measure the size of the class \(\mathcal{F}\). These results are applied to obtain tight upper bounds for the loss of a decision selected by empirical loss minimization from a class of decisions.
    0 references
    Vapnik-Chervonenkis inequality
    0 references
    uniform laws of large numbers
    0 references
    empirical risk minimization
    0 references

    Identifiers