Premium
Quadratic programming algorithms for ensemble models
Author(s) -
Xu Jie,
Gray J. Brian
Publication year - 2012
Publication title -
wiley interdisciplinary reviews: computational statistics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.693
H-Index - 38
eISSN - 1939-0068
pISSN - 1939-5108
DOI - 10.1002/wics.1237
Subject(s) - boosting (machine learning) , computer science , machine learning , ensemble learning , quadratic equation , random forest , artificial intelligence , quadratic programming , algorithm , random subspace method , support vector machine , mathematics , mathematical optimization , geometry
Ensemble models, such as bagging, random forests, and boosting, have better predictive accuracy than single classifiers. These ensembles typically consist of hundreds of single classifiers, which make future predictions and model interpretation much more difficult than for single classifiers. Recently, research efforts have been directed toward improving ensembles by reducing their size while increasing or maintaining their predictive accuracy. In this article, we review recently proposed methods based on quadratic programming techniques for accomplishing these goals. WIREs Comput Stat 2013, 5:41–47. doi: 10.1002/wics.1237 This article is categorized under: Statistical Learning and Exploratory Methods of the Data Sciences > Modeling Methods Algorithms and Computational Methods > Quadratic and Nonlinear Programming