Skip to main navigation Skip to search Skip to main content

Two new regularized AdaBoost algorithms

  • University of Florida

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

10 Scopus citations

Abstract

AdaBoost rarely suffers from overfitting problems in low noise data cases. However, recent studies with highly noisy patterns clearly showed that overfitting can occur. A natural strategy to alleviate the problem is to penalize the distribution skewness in the learning process to prevent several hardest examples from spoiling decision boundaries. In this paper, we describe in detail how a penalty scheme can be pursued in the mathematical programming setting as well as in the Boosting setting. By using two smooth convex penalty functions, two new soft margin concepts are defined and two new regularized AdaBoost algorithms are proposed. The effectiveness of the proposed algorithms is demonstrated through a large scale experiment. Compared with other regularized AdaBoost algorithms, our methods can achieve at least the same or much better performances.

Original languageEnglish
Title of host publicationProceedings of the 2004 International Conference on Machine Learning and Applications, ICMLA '04
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages41-48
Number of pages8
ISBN (Print)0780388232, 9780780388239
DOIs
StatePublished - 2004
Event3rd International Conference on Machine Learning and Applications, ICMLA 2004 - Louisville, KY, United States
Duration: Dec 16 2004Dec 18 2004

Publication series

NameProceedings of the 2004 International Conference on Machine Learning and Applications, ICMLA '04

Conference

Conference3rd International Conference on Machine Learning and Applications, ICMLA 2004
Country/TerritoryUnited States
CityLouisville, KY
Period12/16/0412/18/04

Fingerprint

Dive into the research topics of 'Two new regularized AdaBoost algorithms'. Together they form a unique fingerprint.

Cite this