Optimal aggregation of classifiers in statistical learning
摘要：
Classification can be considered as nonparametric estimation of sets, where the risk is defined by means of a specific distance between sets associated with misclassification error. It is shown that the rates of convergence of classifiers depend on two parameters: the complexity of the class of candidate sets and the margin parameter. The dependence is explicitly given, indicating that optimal fast rates approaching O(n-1) can be attained, where n is the sample size, and that the proposed classifiers have the property of robustness to the margin. The main result of the paper concerns optimal aggregation of classifiers: we suggest a classifier that automatically adapts both to the complexity and to the margin, and attains the optimal fast rates, up to a logarithmic factor.
展开
关键词：
classification statistical learning aggregation of classifiers optimal rates empirical processes margin complexity of classes of sets MODEL SELECTION RATES CLASSIFICATION CONVERGENCE MARGIN ERROR SETS
DOI：
10.1214/aos/1079120131
被引量：
年份：
2004
国家科技图书文献中心
(权威机构)
掌桥科研
Semantic Scholar
dx.doi.org
Oxford Univ Press
查看更多
ProQuest
ResearchGate
Citeseer
hal.univ-brest.fr
mendeley.com
hal.in2p3.fr
zentralblatt-math.org
hal-lirmm.ccsd.cnrs.fr
cds.cern.ch
hal.univ-nantes.fr
proba.jussieu.fr
projecteuclid.org
hal.upmc.fr
hal.inserm.fr
onAcademic
hal.archives-ouvertes.fr
hal.univ-savoie.fr
core.ac.uk
proba.jussieu.fr
(全网免费下载)
proba.jussieu.fr
(全网免费下载)
通过文献互助平台发起求助，成功后即可免费获取论文全文。
相似文献
参考文献
引证文献
辅助模式
引用
文献可以批量引用啦~
欢迎点我试用！
