Please use this identifier to cite or link to this item:
https://hdl.handle.net/2440/67409
Citations | ||
Scopus | Web of Science® | Altmetric |
---|---|---|
?
|
?
|
Type: | Conference paper |
Title: | Boosting the minimum margin: LPBoost vs. AdaBoost |
Author: | Li, H. Shen, C. |
Citation: | Proceedings International Conference on Digital Image Computing: Techniques and Applications (DICTA'08), 1-3 Descember, 2008; pp. 533-539 |
Publisher: | IEEE |
Publisher Place: | Online |
Issue Date: | 2008 |
ISBN: | 9780769534565 |
Conference Name: | Computing: Techniques and Applications. Digital Image (2008 : Canberra, ACT, Australia) |
Statement of Responsibility: | Hanxi Li and Chunhua Shen |
Abstract: | LPBoost seemingly should have better generalization capability than AdaBoost according to the margin theory (Schapire, 1999) because LPBoost optimizes the minimum margin directly. Thus far, however, there is no empirical comparison and theoretical explanation of LPBoost against AdaBoost. We have conducted an experimental evaluation on the classification performance of LPBoost and AdaBoost in this paper. Our results show that the LPBoost performs worse than AdaBoost in most cases. By considering the margin distribution, we present an explanation. Also, our finding indicates that besides the minimum margin, which is directly and globally optimized in LPBoost, the margin distribution plays a more important role in terms of the learned strong classifierpsilas classification performance. |
Rights: | © Copyright 2011 IEEE – All Rights Reserved |
DOI: | 10.1109/DICTA.2008.47 |
Published version: | http://dx.doi.org/10.1109/dicta.2008.47 |
Appears in Collections: | Aurora harvest 5 Computer Science publications |
Files in This Item:
There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.