Advertisement

Complexity Regularization

  • Luc Devroye
  • László Györfi
  • Gábor Lugosi
Part of the Stochastic Modelling and Applied Probability book series (SMAP, volume 31)

Abstract

This chapter offers key theoretical results that confirm the existence of certain “good” rules. Although the proofs are constructive—we do tell you how you may design such rules—the computational requirements are often prohibitive. Many of these rules are thus not likely to filter down to the software packages and pattern recognition implementations. An attempt at reducing the computational complexity somewhat is described in the section entitled “Simple empirical covering.” Nevertheless, we feel that much more serious work on discovering practical algorithms for empirical risk minimization is sorely needed.

Keywords

Decision Rule Error Probability Prove Theorem Classification Rule Minimum Description Length 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Copyright information

© Springer Science+Business Media New York 1996

Authors and Affiliations

  • Luc Devroye
    • 1
  • László Györfi
    • 2
  • Gábor Lugosi
    • 2
  1. 1.School of Computer ScienceMcGill UniversityMontrealCanada
  2. 2.Department of Mathematics and Computer ScienceTechnical University of BudapestBudapestHungary

Personalised recommendations