Please use this identifier to cite or link to this item:
Scopus Web of Science® Altmetric
Type: Journal article
Title: Fully corrective boosting with arbitrary loss and regularization
Author: Shen, C.
Li, H.
Van Den Hengel, A.
Citation: Neural Networks, 2013; 48:44-58
Publisher: Pergamon-Elsevier Science Ltd
Issue Date: 2013
ISSN: 0893-6080
Statement of
Chunhua Shen, Hanxi Li, Anton van den Hengel
Abstract: We propose a general framework for analyzing and developing fully corrective boosting-based classifiers. The framework accepts any convex objective function, and allows any convex (for example, lp-norm, p ≥ 1) regularization term. By placing the wide variety of existing fully corrective boosting-based classifiers on a common footing, and considering the primal and dual problems together, the framework allows direct com- parison between apparently disparate methods. By solving the primal rather than the dual the framework is capable of generating efficient fully-corrective boosting algorithms without recourse to sophisticated convex optimization processes. We show that a range of additional boosting-based algorithms can be incorporated into the framework despite not being fully corrective. Finally, we provide an empirical analysis of the per- formance of a variety of the most significant boosting-based classifiers on a few machine learning benchmark datasets.
Keywords: Boosting; ensemble learning; convex optimization; column generation
Rights: Copyright © 2013 Elsevier Ltd.
RMID: 0020130856
DOI: 10.1016/j.neunet.2013.07.006
Grant ID:
Appears in Collections:Computer Science publications

Files in This Item:
File Description SizeFormat 
hdl_78929.pdfAccepted version549.63 kBAdobe PDFView/Open

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.