de.mpg.escidoc.pubman.appbase.FacesBean
English
 
Help Guide Disclaimer Contact us Login
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT

Released

Conference Paper

Algorithmic Stability and Generalization Performance

MPS-Authors
http://pubman.mpdl.mpg.de/cone/persons/resource/persons83824

Bousquet,  O
Department Empirical Inference, Max Planck Institute for Biological Cybernetics, Max Planck Society;

Locator
There are no locators available
Fulltext (public)
There are no public fulltexts available
Supplementary Material (public)
There is no public supplementary material available
Citation

Bousquet, O. (2001). Algorithmic Stability and Generalization Performance. Advances in Neural Information Processing Systems, 196-202.


Cite as: http://hdl.handle.net/11858/00-001M-0000-0013-E2AA-C
Abstract
We present a novel way of obtaining PAC-style bounds on the generalization error of learning algorithms, explicitly using their stability properties. A \em stable learner being one for which the learned solution does not change much for small changes in the training set. The bounds we obtain do not depend on any measure of the complexity of the hypothesis space (e.g. VC dimension) but rather depend on how the learning algorithm searches this space, and can thus be applied even when the VC dimension in infinite. We demonstrate that regularization networks possess the required stability property and apply our method to obtain new bounds on their generalization performance.