Please use this identifier to cite or link to this item:
|Scopus||Web of Science®||Altmetric|
|Title:||Fully corrective boosting with arbitrary loss and regularization|
Van Den Hengel, A.
|Citation:||Neural Networks, 2013; 48:44-58|
|Publisher:||Pergamon-Elsevier Science Ltd|
|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.|
|Appears in Collections:||Computer Science publications|
Files in This Item:
|hdl_78929.pdf||Accepted version||549.63 kB||Adobe PDF||View/Open|
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.