Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Scale-sensitive dimensions, uniform convergence, and learnability

Scale-sensitive dimensions, uniform convergence, and learnability Learnability in Valiant's PAC learning model has been shown to be strongly related to the existence of uniform laws of large numbers. These laws define a distribution-free convergence property of means to expectations uniformly over classes of random variables. Classes of real-valued functions enjoying such a property are also known as uniform Glivenko-Cantelli classes. In this paper, we prove, through a generalization of Sauer's lemma that may be interesting in its own right, a new characterization of uniform Glivenko-Cantelli classes. Our characterization yields Dudley, Gine´, and Zinn's previous characterization as a corollary. Furthermore, it is the first based on a Gine´, and Zinn's previous characterization as a corollary. Furthermore, it is the first based on a simple combinatorial quantity generalizing the Vapnik-Chervonenkis dimension. We apply this result to obtain the weakest combinatorial condition known to imply PAC learnability in the statistical regression (or “agnostic”) framework. Furthermore, we find a characterization of learnability in the probabilistic concept model, solving an open problem posed by Kearns and Schapire. These results show that the accuracy parameter plays a crucial role in determining the effective complexity of the learner's hypothesis class. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Journal of the ACM (JACM) Association for Computing Machinery

Scale-sensitive dimensions, uniform convergence, and learnability

Download PDF
17 pages

Loading next page...
 
/lp/association-for-computing-machinery/scale-sensitive-dimensions-uniform-convergence-and-learnability-pJoBO0z1dy

References (1)

  • ALON N. (1983)

    265

    Israel J. Math., 45

Publisher
Association for Computing Machinery
Copyright
Copyright © 1997 by ACM Inc.
ISSN
0004-5411
DOI
10.1145/263867.263927
Publisher site
See Article on Publisher Site

Abstract

Learnability in Valiant's PAC learning model has been shown to be strongly related to the existence of uniform laws of large numbers. These laws define a distribution-free convergence property of means to expectations uniformly over classes of random variables. Classes of real-valued functions enjoying such a property are also known as uniform Glivenko-Cantelli classes. In this paper, we prove, through a generalization of Sauer's lemma that may be interesting in its own right, a new characterization of uniform Glivenko-Cantelli classes. Our characterization yields Dudley, Gine´, and Zinn's previous characterization as a corollary. Furthermore, it is the first based on a Gine´, and Zinn's previous characterization as a corollary. Furthermore, it is the first based on a simple combinatorial quantity generalizing the Vapnik-Chervonenkis dimension. We apply this result to obtain the weakest combinatorial condition known to imply PAC learnability in the statistical regression (or “agnostic”) framework. Furthermore, we find a characterization of learnability in the probabilistic concept model, solving an open problem posed by Kearns and Schapire. These results show that the accuracy parameter plays a crucial role in determining the effective complexity of the learner's hypothesis class.

Journal

Journal of the ACM (JACM) – Association for Computing Machinery

Published: Jul 1, 1997

There are no references for this article.