Bernoulli

  • Bernoulli
  • Volume 18, Number 4 (2012), 1310-1319.

Uniform approximation of Vapnik–Chervonenkis classes

Terrence M. Adams and Andrew B. Nobel

Full-text: Open access

Abstract

For any family of measurable sets in a probability space, we show that either (i) the family has infinite Vapnik–Chervonenkis (VC) dimension or (ii) for every $\varepsilon >0$ there is a finite partition $\pi$ such the essential $\pi$-boundary of each set has measure at most $\varepsilon $. Immediate corollaries include the fact that a separable family with finite VC dimension has finite bracketing numbers, and satisfies uniform laws of large numbers for every ergodic process. From these corollaries, we derive analogous results for VC major and VC graph families of functions.

Article information

Source
Bernoulli, Volume 18, Number 4 (2012), 1310-1319.

Dates
First available in Project Euclid: 12 November 2012

Permanent link to this document
https://projecteuclid.org/euclid.bj/1352727812

Digital Object Identifier
doi:10.3150/11-BEJ379

Mathematical Reviews number (MathSciNet)
MR2995797

Zentralblatt MATH identifier
1268.60037

Keywords
bracketing numbers finite approximation uniform law of large numbers Vapnik–Chervonenkis class VC graph class VC major class

Citation

Adams, Terrence M.; Nobel, Andrew B. Uniform approximation of Vapnik–Chervonenkis classes. Bernoulli 18 (2012), no. 4, 1310--1319. doi:10.3150/11-BEJ379. https://projecteuclid.org/euclid.bj/1352727812


Export citation

References

  • [1] Adams, T.M. and Nobel, A.B. (2010). The gap dimension and uniform laws of large numbers for ergodic processes. Preprint. Available at arXiv:1007.2964v1.
  • [2] Adams, T.M. and Nobel, A.B. (2010). Uniform approximation and bracketing properties of VC classes. Preprint. Available at arXiv:1007.4037v1.
  • [3] Adams, T.M. and Nobel, A.B. (2010). Uniform convergence of Vapnik–Chervonenkis classes under ergodic sampling. Ann. Probab. 38 1345–1367.
  • [4] Assouad, P. (1983). Densité et dimension. Ann. Inst. Fourier (Grenoble) 33 233–282.
  • [5] Devroye, L., Györfi, L. and Lugosi, G. (1996). A Probabilistic Theory of Pattern Recognition. Applications of Mathematics (New York) 31. New York: Springer.
  • [6] Dudley, R.M. (1999). Uniform Central Limit Theorems. Cambridge Studies in Advanced Mathematics 63. Cambridge: Cambridge Univ. Press.
  • [7] Gaenssler, P. and Stute, W. (1976). On uniform convergence of measures with applications to uniform convergence of empirical distributions. In Empirical Distributions and Processes (Selected Papers, Meeting on Math. Stochastics, Oberwolfach, 1976). Lecture Notes in Math. 566 45–56. Berlin: Springer.
  • [8] Kearns, M.J. and Schapire, R.E. (1994). Efficient distribution-free learning of probabilistic concepts. J. Comput. System Sci. 48 464–497.
  • [9] Matoušek, J. (2002). Lectures on Discrete Geometry. Graduate Texts in Mathematics 212. New York: Springer.
  • [10] Pollard, D. (1984). Convergence of Stochastic Processes. Springer Series in Statistics. New York: Springer.
  • [11] Talagrand, M. (1987). The Glivenko–Cantelli problem. Ann. Probab. 15 837–870.
  • [12] van der Vaart, A.W. and Wellner, J.A. (1996). Weak Convergence and Empirical Processes: With Applications to Statistics. Springer Series in Statistics. New York: Springer.
  • [13] Vapnik, V.N. (2000). The Nature of Statistical Learning Theory, 2nd ed. Statistics for Engineering and Information Science. New York: Springer.
  • [14] Vapnik, V.N. and Chervonenkis, A.Y. (1971). On the uniform convergence of relative frequencies of events to their probabilities. Theory Probab. Appl. 16 264–280.
  • [15] von Handel, R. (2011). The universal Glivenko–Cantelli property. Preprint. Available at ArXiv:1009.4434v3.