Improved Risk Tail Bounds for On-Line Algorithms
摘要：
Tight bounds are derived on the risk of models in the ensemble generated by incremental training of an arbitrary learning algorithm. The result is based on proof techniques that are remarkably different from the standard risk analysis based on uniform convergence arguments, and improves on previous bounds published by the same authors.
展开
关键词：
learning (artificial intelligence) risk analysis statistical analysis arbitrary learning algorithm ensemble incremental training online algorithms proof techniques risk analysis risk tail bounds statistical learning theory uniform convergence arguments M
DOI：
10.1109/TIT.2007.911292
被引量：
年份：
2008
国家科技图书文献中心
(权威机构)
IEEEXplore
(全网免费下载)
IEEEXplore
Semantic Scholar
(全网免费下载)
掌桥科研
查看更多
Ingenta
dx.doi.org
ACM
ResearchGate
ProQuest
ResearchGate
(全网免费下载)
Citeseer
(全网免费下载)
EBSCO
Citeseer
EBSCO
machinelearning.wustl.edu
(全网免费下载)
mendeley.com
cs.duke.edu
(全网免费下载)
homes.di.unimi.it
(全网免费下载)
homes.dsi.unimi.it
(全网免费下载)
deepdyve.com
pdf.aminer.org
(全网免费下载)
core.ac.uk
dicom.uninsubria.it
(全网免费下载)
air.unimi.it
dista.uninsubria.it
(全网免费下载)
core.kmi.open.ac.uk
(全网免费下载)
eprints.pascal-network.org
(全网免费下载)
hdl.handle.net
onAcademic
videolectures.net
mercurio.srv.di.unimi.it
(全网免费下载)
mercurio.srv.dsi.unimi.it
(全网免费下载)
oldbooks.nips.cc
(全网免费下载)
papers.nips.cc
学术范
papers.nips.cc
(全网免费下载)
translectures.videolectures.net
(全网免费下载)
videolectures.net
(全网免费下载)
eprints.pascal-network.org
machinelearning.wustl.edu
core.kmi.open.ac.uk
zentralblatt-math.org
学术范
(全网免费下载)
IEEEXplore
(全网免费下载)
Semantic Scholar
(全网免费下载)
ResearchGate
(全网免费下载)
Citeseer
(全网免费下载)
dicom.uninsubria.it
(全网免费下载)
cs.duke.edu
(全网免费下载)
translectures.videolectures.net
(全网免费下载)
videolectures.net
(全网免费下载)
pdf.aminer.org
(全网免费下载)
papers.nips.cc
(全网免费下载)
mercurio.srv.di.unimi.it
(全网免费下载)
machinelearning.wustl.edu
(全网免费下载)
oldbooks.nips.cc
(全网免费下载)
homes.di.unimi.it
(全网免费下载)
mercurio.srv.dsi.unimi.it
(全网免费下载)
homes.dsi.unimi.it
(全网免费下载)
eprints.pascal-network.org
(全网免费下载)
学术范
(全网免费下载)
core.kmi.open.ac.uk
(全网免费下载)
dista.uninsubria.it
(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
引用走势
辅助模式
引用
文献可以批量引用啦~
欢迎点我试用！
