A Better Variance Control for Pac-bayesian Classification

  title={A Better Variance Control for Pac-bayesian Classification},
  author={J Audibert},
The common method to understand and improve classification rules is to prove bounds on the generalization error. Here we provide localized data-based PAC-bounds for the difference between the risk of any two randomized estimators. We derive from these bounds two types of algorithms: the first one uses combinatorial technics and is related to compression schemes whereas the second one involves Gibbs estimators. We also recover some of the results of the Vapnik-Chervonenkis theory and improve… CONTINUE READING
Highly Cited
This paper has 21 citations. REVIEW CITATIONS


Publications referenced by this paper.
Showing 1-4 of 4 references

Classification using Gibbs estimators under complexity and margin assumptions, Preprint

  • J.-Y. Audibert
  • Laboratoire de Probabilité et Modelès Ale…
  • 2004
Highly Influential
3 Excerpts

Concentration inequalities and empirical processes theory applied to the analysis of learning algorithms

  • O. Bousquet
  • Ph.D. thesis, Department of Applied Mathematics…
  • 2002
1 Excerpt

Similar Papers

Loading similar papers…