English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
Add to Basket
 DetailsSummary
  On the Convergence of Leveraging

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

Item is

 

show all hide all

Basic

show hide
Item Permalink: https://hdl.handle.net/11858/00-001M-0000-0013-DF0F-0 Version Permalink: https://hdl.handle.net/11858/00-001M-0000-0013-DF10-A
Genre: Conference Paper

Files

show Files

Locators

show

Creators

show
hide
 Creators:
Rätsch, G1, Author           
Mika, S, Author
Warmuth, MK, Author
Dietterich, Editor
T.G., Editor
Becker, S., Editor
Ghahramani, Z., Editor
Affiliations:
1Department Empirical Inference, Max Planck Institute for Biological Cybernetics, Max Planck Society, ou_1497795              

Content

show
hide
Free keywords: -
 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.

Details

show
hide
Language(s):
 Dates: 2002-09
 Publication Status: Issued
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: ISBN: 0-262-04208-8
URI: http://books.nips.cc/nips14.html
BibTex Citekey: 2184
 Degree: -

Event

show
hide
Title: Fifteenth Annual Neural Information Processing Systems Conference (NIPS 2001)
Place of Event: Vancouver, BC, Canada
Start-/End Date: -

Legal Case

show

Project information

show

Source 1

show
hide
Title: Advances in Neural Information Processing Systems
Source Genre: Journal
 Creator(s):
Affiliations:
Publ. Info: Cambridge, MA, USA : MIT Press
Pages: - Volume / Issue: - Sequence Number: - Start / End Page: 487 - 494 Identifier: -