Skip to main content
SpringerLink
Log in

Classes of Functions Related to VC Properties

  • Chapter
  • First Online:
Measures of Complexity

  • 2842 Accesses

Abstract

The notion of Vapnik–Chervonenkis (VC) class of sets can be extended to classes of functions in a few ways. Under further hypotheses, central limit theorems for empirical measures can be proved uniformly over such classes. Specific such classes on Euclidean spaces can be used to show the existence of location vector and scatter matrix functionals, replacing mean vectors and covariance matrices, but on classes of probability measures P that are weakly dense, weakly open, and so contain arbitrarily heavy-tailed distributions.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
eBook
USD 16.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 109.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info
Hardcover Book
USD 109.99
Price excludes VAT (USA)
  • Durable hardcover edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

References

  1. Alexander, K.S.: Probability inequalities for empirical processes and a law of the iterated logarithm. Ann. Probab. 12(4), 1041–1067 (1984). Correction, 15, 428–430 (1987)

    Google Scholar 

  2. Alexander, K.S.: The central limit theorem for empirical processes on Vapnik-Červonenkis classes. Ann. Probab. 15(1), 178–203 (1987)

    Article  MATH  MathSciNet  Google Scholar 

  3. Alon, N., Ben-David, S., Cesa-Bianchi, N., Haussler, D.: Scale-sensitive dimensions, uniform convergence, and learnability. J. ACM 44(4), 615–631 (1997)

    Article  MATH  MathSciNet  Google Scholar 

  4. Ando, R.K., Zhang, T.: A framework for learning predictive structures from multiple tasks and unlabeled data. J. Mach. Learn. Res. 6, 1817–1853 (2005)

    MATH  MathSciNet  Google Scholar 

  5. Bousquet, O., Koltchinskii, V., Panchenko, D.: Some local measures of complexity of convex hulls and generalization bounds. In: Kivinen, J., Sloan, R.H. (eds.) Proceedings of Conference on Computational Learning Theory, COLT Sydney. Lecture Notes in Computer Science, vol. 2375, pp. 59–73. Springer, New York (2002)

    Google Scholar 

  6. Chae, S.B.: Holomorphy and Calculus in Normed Spaces. CRC, New York (1985)

    MATH  Google Scholar 

  7. Cover, T.M.: Geometrical and statistical properties of systems of linear inequalities with applications in pattern recognition. IEEE Trans. Electron. Comput. EC-14, 326–334 (1965)

    Google Scholar 

  8. Dudley, R.M.: Central limit theorems for empirical measures. Ann. Probab. 6(6), 899–929 (1978). Correction 7, 909–911 (1979)

    Google Scholar 

  9. Dudley, R.M.: Vapnik-Červonenkis Donsker classes of functions. In: Proceedings of Conference “Aspects Statistiques et Aspects Physiques des Processus Gaussiens”, St-Flour, 1980, Colloq. Internat. CNRS, vol. 307, pp. 251–269. Paris, 1981

    Google Scholar 

  10. Dudley, R.M.: Universal Donsker classes and metric entropy. Ann. Probab. 15(4), 1306–1326 (1987)

    Article  MATH  MathSciNet  Google Scholar 

  11. Dudley, R.M.: Some facts about functionals of location and scatter. In: E. Giné, V. Koltchinskii, W. Li, J. Zinn (eds.) High Dimensional Probability, Proceedings of 4th International Conference, IMS Lecture Notes Monograph Series, vol. 51, pp. 207–219 (2006)

    Google Scholar 

  12. Dudley, R.M.: Uniform Central Limit Theorems, 2nd edn. Cambridge University Press, Cambridge (2014)

    Google Scholar 

  13. Dudley, R.M., Giné, E., Zinn, J.: Universal and uniform Glivenko-Cantelli classes. J. Theor. Probab. 4(3), 485–510 (1991)

    Article  MATH  Google Scholar 

  14. Dudley, R.M., Norvaiša, R.: Concrete Functional Calculus. Springer, New York (2010)

    Google Scholar 

  15. Dudley, R.M., Sidenko, S., Wang, Z.: Differentiability of \(M\) likelihoods. Technical report (2009). http://arxiv.org/abs/0801.3052v2

  16. Dudley, R.M., Sidenko, S., Wang, Z.: Differentiability of \(t\)-functionals of location and scatter. Ann. Stat. 37(2), 939–960 (2009)

    Article  MATH  MathSciNet  Google Scholar 

  17. Giné, E., Zinn, J.: Gaussian characterization of uniform Donsker classes of functions. Ann. Probab. 19(2), 758–782 (1991)

    Article  MATH  MathSciNet  Google Scholar 

  18. Kent, J.T., Tyler, D.E.: Redescending \(M\)-estimates of multivariate location and scatter. Ann. Stat. 19(4), 2102–2119 (1991)

    Article  MATH  MathSciNet  Google Scholar 

  19. Kent, J.T., Tyler, D.E., Vardi, Y.: A curious likelihood identity for the multivariate \(T\)-distribution. Commun. Stat.–Simul. 23(2), 441–453 (1994)

    Google Scholar 

  20. Obenchain, R.L.: Multivariate procedures invariant under linear transformations. Ann. Math. Stat. 42(5), 1569–1578 (1971)

    Article  MATH  MathSciNet  Google Scholar 

  21. Pollard, D.: A central limit theorem for empirical processes. J. Aust. Math. Soc. Ser. A 33, 235–248 (1982)

    Article  MATH  MathSciNet  Google Scholar 

  22. Pollard, D.: Convergence of Stochastic Processes. Springer, New York (1984)

    Book  MATH  Google Scholar 

  23. Schläfli, L.: Theorie der vielfachen Kontinuität (Theory of Multidimensional Continua, in German). Denkschriften der Schweizer. Naturforschenden Gesellschaft (Memoirs of the Swiss Scientific Society) (1901). Republished, Cornell University Library, 1991

    Google Scholar 

  24. Van der Vaart, A.W., Wellner, J.: Weak Convergence and Empirical Processes. Springer, New York (1996)

    Book  MATH  Google Scholar 

  25. Vapnik, V.N.: The Nature of Statistical Learning Theory. Springer, New York (1995)

    Book  MATH  Google Scholar 

  26. Vapnik, V.N., Chervonenkis, A.Y.: On the uniform convergence of relative frequencies of events to their probabilities (translated from Russian). Theory Probab. Appl. 16, 264–280. (Chapter 3 of this volume)

    Google Scholar 

  27. Vapnik, V.N., Chervonenkis, A.Y.: Necessary and sufficient conditions for the uniform convergence of means to their expectations (translated from Russian). Theory Probab. Appl. 26, 532–553 (1982)

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Mathematics, Massachusetts Institute of Technology, Cambridge, MA, USA

    R. M. Dudley

Authors
  1. R. M. Dudley
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to R. M. Dudley .

Editor information

Editors and Affiliations

  1. Dept. of Computer Science, Royal Holloway, Univ of London, Egham, Surrey, United Kingdom

    Vladimir Vovk

  2. Frederick University, Nicosia, Cyprus

    Harris Papadopoulos

  3. Dept. of Computer Science, University of London, Egham, Surrey, United Kingdom

    Alexander Gammerman

Rights and permissions

Reprints and permissions

Copyright information

© 2015 Springer International Publishing Switzerland

About this chapter

Cite this chapter

Dudley, R.M. (2015). Classes of Functions Related to VC Properties. In: Vovk, V., Papadopoulos, H., Gammerman, A. (eds) Measures of Complexity. Springer, Cham. https://doi.org/10.1007/978-3-319-21852-6_14

Download citation

  • DOI: https://doi.org/10.1007/978-3-319-21852-6_14

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-319-21851-9

  • Online ISBN: 978-3-319-21852-6

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation