Capacity dependent estimations by integral operator techniques

In this paper, we study the learning performance of least square regularized regression based on some capacity conditions. An iid setting is considered, where the sequence of probability measures for sampling is identical and the samples are independently drawn. We improve the learning rate to O(m -...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Qin Guo, Yukui Zhu, Hongwei Sun
Format: Tagungsbericht
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page 3089
container_issue
container_start_page 3086
container_title
container_volume 7
creator Qin Guo
Yukui Zhu
Hongwei Sun
description In this paper, we study the learning performance of least square regularized regression based on some capacity conditions. An iid setting is considered, where the sequence of probability measures for sampling is identical and the samples are independently drawn. We improve the learning rate to O(m -β/(1+2β) ) by integral operator techniques.
doi_str_mv 10.1109/CISP.2010.5648072
format Conference Proceeding
fullrecord <record><control><sourceid>ieee_6IE</sourceid><recordid>TN_cdi_ieee_primary_5648072</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>5648072</ieee_id><sourcerecordid>5648072</sourcerecordid><originalsourceid>FETCH-LOGICAL-i90t-f3dcb2e2c2633a042776a1b4219456231365a3f621950936e82b6f37ffb315253</originalsourceid><addsrcrecordid>eNo1j81KxDAUhSMiqGMfQNzkBTom9-an3QhS_BkYUHD2Q9LeaGRsaxMXfXsLjmdz-DYf5zB2LcVaSlHfNpu31zWIBbVRlbBwworaVlKBUkZLbU7Z5T8gnrMipU-xRINFaS7YXeNG18Y8845G6jvqM6eU45fLcegT9zOPfab3yR34MNLk8jDxTO1HH79_KF2xs-AOiYpjr9ju8WHXPJfbl6dNc78tYy1yGbBrPRC0YBCdUGCtcdIrkLXSBlCi0Q6DWViLGg1V4E1AG4JHqUHjit38aSMR7cdpmTfN--Nj_AX_XUjX</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Capacity dependent estimations by integral operator techniques</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Qin Guo ; Yukui Zhu ; Hongwei Sun</creator><creatorcontrib>Qin Guo ; Yukui Zhu ; Hongwei Sun</creatorcontrib><description>In this paper, we study the learning performance of least square regularized regression based on some capacity conditions. An iid setting is considered, where the sequence of probability measures for sampling is identical and the samples are independently drawn. We improve the learning rate to O(m -β/(1+2β) ) by integral operator techniques.</description><identifier>ISBN: 1424465133</identifier><identifier>ISBN: 9781424465132</identifier><identifier>EISBN: 9781424465156</identifier><identifier>EISBN: 1424465168</identifier><identifier>EISBN: 9781424465163</identifier><identifier>EISBN: 142446515X</identifier><identifier>DOI: 10.1109/CISP.2010.5648072</identifier><language>eng</language><publisher>IEEE</publisher><subject>Algorithm design and analysis ; Approximation error ; Educational institutions ; Eigenvalues and eigenfunctions ; Kernel ; Least squares approximation ; Sun</subject><ispartof>2010 3rd International Congress on Image and Signal Processing, 2010, Vol.7, p.3086-3089</ispartof><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/5648072$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,780,784,789,790,2058,27925,54920</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/5648072$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Qin Guo</creatorcontrib><creatorcontrib>Yukui Zhu</creatorcontrib><creatorcontrib>Hongwei Sun</creatorcontrib><title>Capacity dependent estimations by integral operator techniques</title><title>2010 3rd International Congress on Image and Signal Processing</title><addtitle>CISP</addtitle><description>In this paper, we study the learning performance of least square regularized regression based on some capacity conditions. An iid setting is considered, where the sequence of probability measures for sampling is identical and the samples are independently drawn. We improve the learning rate to O(m -β/(1+2β) ) by integral operator techniques.</description><subject>Algorithm design and analysis</subject><subject>Approximation error</subject><subject>Educational institutions</subject><subject>Eigenvalues and eigenfunctions</subject><subject>Kernel</subject><subject>Least squares approximation</subject><subject>Sun</subject><isbn>1424465133</isbn><isbn>9781424465132</isbn><isbn>9781424465156</isbn><isbn>1424465168</isbn><isbn>9781424465163</isbn><isbn>142446515X</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2010</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><sourceid>RIE</sourceid><recordid>eNo1j81KxDAUhSMiqGMfQNzkBTom9-an3QhS_BkYUHD2Q9LeaGRsaxMXfXsLjmdz-DYf5zB2LcVaSlHfNpu31zWIBbVRlbBwworaVlKBUkZLbU7Z5T8gnrMipU-xRINFaS7YXeNG18Y8845G6jvqM6eU45fLcegT9zOPfab3yR34MNLk8jDxTO1HH79_KF2xs-AOiYpjr9ju8WHXPJfbl6dNc78tYy1yGbBrPRC0YBCdUGCtcdIrkLXSBlCi0Q6DWViLGg1V4E1AG4JHqUHjit38aSMR7cdpmTfN--Nj_AX_XUjX</recordid><startdate>201010</startdate><enddate>201010</enddate><creator>Qin Guo</creator><creator>Yukui Zhu</creator><creator>Hongwei Sun</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope></search><sort><creationdate>201010</creationdate><title>Capacity dependent estimations by integral operator techniques</title><author>Qin Guo ; Yukui Zhu ; Hongwei Sun</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i90t-f3dcb2e2c2633a042776a1b4219456231365a3f621950936e82b6f37ffb315253</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2010</creationdate><topic>Algorithm design and analysis</topic><topic>Approximation error</topic><topic>Educational institutions</topic><topic>Eigenvalues and eigenfunctions</topic><topic>Kernel</topic><topic>Least squares approximation</topic><topic>Sun</topic><toplevel>online_resources</toplevel><creatorcontrib>Qin Guo</creatorcontrib><creatorcontrib>Yukui Zhu</creatorcontrib><creatorcontrib>Hongwei Sun</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE Electronic Library (IEL)</collection><collection>IEEE Proceedings Order Plans (POP All) 1998-Present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Qin Guo</au><au>Yukui Zhu</au><au>Hongwei Sun</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Capacity dependent estimations by integral operator techniques</atitle><btitle>2010 3rd International Congress on Image and Signal Processing</btitle><stitle>CISP</stitle><date>2010-10</date><risdate>2010</risdate><volume>7</volume><spage>3086</spage><epage>3089</epage><pages>3086-3089</pages><isbn>1424465133</isbn><isbn>9781424465132</isbn><eisbn>9781424465156</eisbn><eisbn>1424465168</eisbn><eisbn>9781424465163</eisbn><eisbn>142446515X</eisbn><abstract>In this paper, we study the learning performance of least square regularized regression based on some capacity conditions. An iid setting is considered, where the sequence of probability measures for sampling is identical and the samples are independently drawn. We improve the learning rate to O(m -β/(1+2β) ) by integral operator techniques.</abstract><pub>IEEE</pub><doi>10.1109/CISP.2010.5648072</doi><tpages>4</tpages></addata></record>
fulltext fulltext_linktorsrc
identifier ISBN: 1424465133
ispartof 2010 3rd International Congress on Image and Signal Processing, 2010, Vol.7, p.3086-3089
issn
language eng
recordid cdi_ieee_primary_5648072
source IEEE Electronic Library (IEL) Conference Proceedings
subjects Algorithm design and analysis
Approximation error
Educational institutions
Eigenvalues and eigenfunctions
Kernel
Least squares approximation
Sun
title Capacity dependent estimations by integral operator techniques
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-24T01%3A20%3A58IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-ieee_6IE&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=Capacity%20dependent%20estimations%20by%20integral%20operator%20techniques&rft.btitle=2010%203rd%20International%20Congress%20on%20Image%20and%20Signal%20Processing&rft.au=Qin%20Guo&rft.date=2010-10&rft.volume=7&rft.spage=3086&rft.epage=3089&rft.pages=3086-3089&rft.isbn=1424465133&rft.isbn_list=9781424465132&rft_id=info:doi/10.1109/CISP.2010.5648072&rft_dat=%3Cieee_6IE%3E5648072%3C/ieee_6IE%3E%3Curl%3E%3C/url%3E&rft.eisbn=9781424465156&rft.eisbn_list=1424465168&rft.eisbn_list=9781424465163&rft.eisbn_list=142446515X&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=5648072&rfr_iscdi=true