Empirical Inference

Stability and Generalization

2002

Article

ei


We define notions of stability for learning algorithms and show how to use these notions to derive generalization error bounds based on the empirical error and the leave-one-out error. The methods we use can be applied in the regression framework as well as in the classification one when the classifier is obtained by thresholding a real-valued function. We study the stability properties of large classes of learning algorithms such as regularization based algorithms. In particular we focus on Hilbert space regularization and Kullback-Leibler regularization. We demonstrate how to apply the results to SVM for regression and classification.

Author(s): Bousquet, O. and Elisseeff, A.
Journal: Journal of Machine Learning Research
Volume: 2
Pages: 499-526
Year: 2002
Day: 0

Department(s): Empirical Inference
Bibtex Type: Article (article)

Digital: 0
Organization: Max-Planck-Gesellschaft
School: Biologische Kybernetik

Links: PDF
PostScript

BibTex

@article{1439,
  title = {Stability and Generalization},
  author = {Bousquet, O. and Elisseeff, A.},
  journal = {Journal of Machine Learning Research},
  volume = {2},
  pages = {499-526},
  organization = {Max-Planck-Gesellschaft},
  school = {Biologische Kybernetik},
  year = {2002},
  doi = {}
}