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

Item

ITEM ACTIONSEXPORT

Released

Conference Paper

On the Convergence of Leveraging

MPS-Authors
http://pubman.mpdl.mpg.de/cone/persons/resource/persons84153

Rätsch,  G
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

Rätsch, G., Mika, S., & Warmuth, M. (2002). On the Convergence of Leveraging. Advances in Neural Information Processing Systems, 487-494.


Cite as: http://hdl.handle.net/11858/00-001M-0000-0013-DF0F-0
Abstract
We give an unified convergence analysis of ensemble learning methods including e.g. AdaBoost, Logistic Regression and the Least-Square-Boost algorithm for regression. These methods have in common that they iteratively call a base learning algorithm which returns hypotheses that are then linearly combined. We show that these methods are related to the Gauss-Southwell method known from numerical optimization and state non-asymptotical convergence results for all these methods. Our analysis includes ℓ1-norm regularized cost functions leading to a clean and general way to regularize ensemble learning.