Asymptotic optimality for consensus-type stochastic approximation algorithms using iterate averaging

This paper introduces a post-iteration averaging algorithm to achieve asymptotic optimality in convergence rates of stochastic approximation algorithms for consensus control with structural constraints. The algorithm involves two stages. The first stage is a coarse approximation obtained using a seq...

Full description

Saved in:
Bibliographic Details
Published in:Journal of control theory and applications 2013-02, Vol.11 (1), p.1-9
Main Authors: Yin, Gang, Wang, Le Yi, Sun, Yu, Casbeer, David, Holsapple, Raymond, Kingston, Derek
Format: Article
Language:English
Subjects:
Algorithms
Approximation
Asymptotic properties
Complexity
Computational Intelligence
Control
Control and Systems Theory
Control theory
Convergence
Engineering
Mathematical analysis
Mechatronics
Optimization
Robotics
Stochasticity
Systems Theory
平均
最优收敛速度
渐近方差
渐近最优
渐近有效
近似算法
迭代点
随机逼近算法
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by cdi_FETCH-LOGICAL-c2971-db69b2d8c8547b71ee9cfd4a5b653659da0041eba3f43965c0cc4941825a9f583
cites cdi_FETCH-LOGICAL-c2971-db69b2d8c8547b71ee9cfd4a5b653659da0041eba3f43965c0cc4941825a9f583
container_end_page 9
container_issue 1
container_start_page 1
container_title Journal of control theory and applications
container_volume 11
creator Yin, Gang
Wang, Le Yi
Sun, Yu
Casbeer, David
Holsapple, Raymond
Kingston, Derek
description This paper introduces a post-iteration averaging algorithm to achieve asymptotic optimality in convergence rates of stochastic approximation algorithms for consensus control with structural constraints. The algorithm involves two stages. The first stage is a coarse approximation obtained using a sequence of large stepsizes. Then, the second stage provides a refinement by averaging the iterates from the first stage. We show that the new algorithm is asymptotically efficient and gives the optimal convergence rates in the sense of the best scaling factor and ＇smallest＇ possible asymptotic variance.
doi_str_mv 10.1007/s11768-013-2013-2
format article
fullrecord <record><control><sourceid>wanfang_jour_proqu</sourceid><recordid>TN_cdi_wanfang_journals_kzllyyy_e201301001</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><cqvip_id>44519257</cqvip_id><wanfj_id>kzllyyy_e201301001</wanfj_id><sourcerecordid>kzllyyy_e201301001</sourcerecordid><originalsourceid>FETCH-LOGICAL-c2971-db69b2d8c8547b71ee9cfd4a5b653659da0041eba3f43965c0cc4941825a9f583</originalsourceid><addsrcrecordid>eNp9kE1LxDAQhosoqKs_wFu9iVDNZ9scRfwCwYueQ5qm3a7dpGZStf56s1vRm5eZEJ533pk3SU4wusAIFZeAcZGXGcI0I9uykxxgIWiGckJ34zsvSJZThvaTQ4AVQpyxojxI6iuY1kNwodOpG0K3Vn0XprRxPtXOgrEwQhamwaQQnF4q2IBqGLz7jGzonE1V3zrfheUa0hE626ZdMF4Fk6r32Nv4c5TsNaoHc_zTF8nL7c3z9X32-HT3cH31mGkiCpzVVS4qUpe65KyoCmyM0E3NFK9yTnMuaoUQw6ZStGFU5FwjrZlguCRciYaXdJGcz3M_lG2UbeXKjd5GR_n61ffTNEmzCQfFxHCEz2Y43vI2Gghy3YE2fa-scSPImBhmBDNGI4pnVHsH4E0jBx-v95PESG7il3P8Mo6VZFuihswaiKxtjf9b5j_R6Y_R0tn2Lep-nRjjWBBe0G-q65Vs</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>1671421443</pqid></control><display><type>article</type><title>Asymptotic optimality for consensus-type stochastic approximation algorithms using iterate averaging</title><source>Springer Nature</source><creator>Yin, Gang ; Wang, Le Yi ; Sun, Yu ; Casbeer, David ; Holsapple, Raymond ; Kingston, Derek</creator><creatorcontrib>Yin, Gang ; Wang, Le Yi ; Sun, Yu ; Casbeer, David ; Holsapple, Raymond ; Kingston, Derek</creatorcontrib><description>This paper introduces a post-iteration averaging algorithm to achieve asymptotic optimality in convergence rates of stochastic approximation algorithms for consensus control with structural constraints. The algorithm involves two stages. The first stage is a coarse approximation obtained using a sequence of large stepsizes. Then, the second stage provides a refinement by averaging the iterates from the first stage. We show that the new algorithm is asymptotically efficient and gives the optimal convergence rates in the sense of the best scaling factor and ＇smallest＇ possible asymptotic variance.</description><identifier>ISSN: 1672-6340</identifier><identifier>EISSN: 1993-0623</identifier><identifier>DOI: 10.1007/s11768-013-2013-2</identifier><language>eng</language><publisher>Heidelberg: South China University of Technology and Academy of Mathematics and Systems Science, CAS</publisher><subject>Algorithms ; Approximation ; Asymptotic properties ; Complexity ; Computational Intelligence ; Control ; Control and Systems Theory ; Control theory ; Convergence ; Engineering ; Mathematical analysis ; Mechatronics ; Optimization ; Robotics ; Stochasticity ; Systems Theory ; 平均 ; 最优收敛速度 ; 渐近方差 ; 渐近最优 ; 渐近有效 ; 近似算法 ; 迭代点 ; 随机逼近算法</subject><ispartof>Journal of control theory and applications, 2013-02, Vol.11 (1), p.1-9</ispartof><rights>South China University of Technology, Academy of Mathematics and Systems Science, Chinese Academy of Sciences and Springer-Verlag Berlin Heidelberg 2013</rights><rights>Copyright © Wanfang Data Co. Ltd. All Rights Reserved.</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c2971-db69b2d8c8547b71ee9cfd4a5b653659da0041eba3f43965c0cc4941825a9f583</citedby><cites>FETCH-LOGICAL-c2971-db69b2d8c8547b71ee9cfd4a5b653659da0041eba3f43965c0cc4941825a9f583</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Uhttp://image.cqvip.com/vip1000/qk/87672X/87672X.jpg</thumbnail><link.rule.ids>314,780,784,27924,27925</link.rule.ids></links><search><creatorcontrib>Yin, Gang</creatorcontrib><creatorcontrib>Wang, Le Yi</creatorcontrib><creatorcontrib>Sun, Yu</creatorcontrib><creatorcontrib>Casbeer, David</creatorcontrib><creatorcontrib>Holsapple, Raymond</creatorcontrib><creatorcontrib>Kingston, Derek</creatorcontrib><title>Asymptotic optimality for consensus-type stochastic approximation algorithms using iterate averaging</title><title>Journal of control theory and applications</title><addtitle>J. Control Theory Appl</addtitle><addtitle>Journal of Control Theory and Applications</addtitle><description>This paper introduces a post-iteration averaging algorithm to achieve asymptotic optimality in convergence rates of stochastic approximation algorithms for consensus control with structural constraints. The algorithm involves two stages. The first stage is a coarse approximation obtained using a sequence of large stepsizes. Then, the second stage provides a refinement by averaging the iterates from the first stage. We show that the new algorithm is asymptotically efficient and gives the optimal convergence rates in the sense of the best scaling factor and ＇smallest＇ possible asymptotic variance.</description><subject>Algorithms</subject><subject>Approximation</subject><subject>Asymptotic properties</subject><subject>Complexity</subject><subject>Computational Intelligence</subject><subject>Control</subject><subject>Control and Systems Theory</subject><subject>Control theory</subject><subject>Convergence</subject><subject>Engineering</subject><subject>Mathematical analysis</subject><subject>Mechatronics</subject><subject>Optimization</subject><subject>Robotics</subject><subject>Stochasticity</subject><subject>Systems Theory</subject><subject>平均</subject><subject>最优收敛速度</subject><subject>渐近方差</subject><subject>渐近最优</subject><subject>渐近有效</subject><subject>近似算法</subject><subject>迭代点</subject><subject>随机逼近算法</subject><issn>1672-6340</issn><issn>1993-0623</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2013</creationdate><recordtype>article</recordtype><recordid>eNp9kE1LxDAQhosoqKs_wFu9iVDNZ9scRfwCwYueQ5qm3a7dpGZStf56s1vRm5eZEJ533pk3SU4wusAIFZeAcZGXGcI0I9uykxxgIWiGckJ34zsvSJZThvaTQ4AVQpyxojxI6iuY1kNwodOpG0K3Vn0XprRxPtXOgrEwQhamwaQQnF4q2IBqGLz7jGzonE1V3zrfheUa0hE626ZdMF4Fk6r32Nv4c5TsNaoHc_zTF8nL7c3z9X32-HT3cH31mGkiCpzVVS4qUpe65KyoCmyM0E3NFK9yTnMuaoUQw6ZStGFU5FwjrZlguCRciYaXdJGcz3M_lG2UbeXKjd5GR_n61ffTNEmzCQfFxHCEz2Y43vI2Gghy3YE2fa-scSPImBhmBDNGI4pnVHsH4E0jBx-v95PESG7il3P8Mo6VZFuihswaiKxtjf9b5j_R6Y_R0tn2Lep-nRjjWBBe0G-q65Vs</recordid><startdate>20130201</startdate><enddate>20130201</enddate><creator>Yin, Gang</creator><creator>Wang, Le Yi</creator><creator>Sun, Yu</creator><creator>Casbeer, David</creator><creator>Holsapple, Raymond</creator><creator>Kingston, Derek</creator><general>South China University of Technology and Academy of Mathematics and Systems Science, CAS</general><general>Department of Mathematics, Wayne State University, Detroit, MI 48202, U.S.A.%Department of Electrical and Computer Engineering, Wayne State University, Detroit, MI 48202, U.S.A.%Quantitative Business Analysis Department, Siena College, Loudonville, New York 12211, U.S.A.%Control Science Center of Excellence, Air Force Research Laboratory, Wright-Patterson AFB, OH 45433, U.S.A</general><scope>2RA</scope><scope>92L</scope><scope>CQIGP</scope><scope>W92</scope><scope>~WA</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7SP</scope><scope>8FD</scope><scope>L7M</scope><scope>2B.</scope><scope>4A8</scope><scope>92I</scope><scope>93N</scope><scope>PSX</scope><scope>TCJ</scope></search><sort><creationdate>20130201</creationdate><title>Asymptotic optimality for consensus-type stochastic approximation algorithms using iterate averaging</title><author>Yin, Gang ; Wang, Le Yi ; Sun, Yu ; Casbeer, David ; Holsapple, Raymond ; Kingston, Derek</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c2971-db69b2d8c8547b71ee9cfd4a5b653659da0041eba3f43965c0cc4941825a9f583</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2013</creationdate><topic>Algorithms</topic><topic>Approximation</topic><topic>Asymptotic properties</topic><topic>Complexity</topic><topic>Computational Intelligence</topic><topic>Control</topic><topic>Control and Systems Theory</topic><topic>Control theory</topic><topic>Convergence</topic><topic>Engineering</topic><topic>Mathematical analysis</topic><topic>Mechatronics</topic><topic>Optimization</topic><topic>Robotics</topic><topic>Stochasticity</topic><topic>Systems Theory</topic><topic>平均</topic><topic>最优收敛速度</topic><topic>渐近方差</topic><topic>渐近最优</topic><topic>渐近有效</topic><topic>近似算法</topic><topic>迭代点</topic><topic>随机逼近算法</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Yin, Gang</creatorcontrib><creatorcontrib>Wang, Le Yi</creatorcontrib><creatorcontrib>Sun, Yu</creatorcontrib><creatorcontrib>Casbeer, David</creatorcontrib><creatorcontrib>Holsapple, Raymond</creatorcontrib><creatorcontrib>Kingston, Derek</creatorcontrib><collection>维普_期刊</collection><collection>中文科技期刊数据库-CALIS站点</collection><collection>维普中文期刊数据库</collection><collection>中文科技期刊数据库-工程技术</collection><collection>中文科技期刊数据库- 镜像站点</collection><collection>CrossRef</collection><collection>Electronics &amp; Communications Abstracts</collection><collection>Technology Research Database</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Wanfang Data Journals - Hong Kong</collection><collection>WANFANG Data Centre</collection><collection>Wanfang Data Journals</collection><collection>万方数据期刊 - 香港版</collection><collection>China Online Journals (COJ)</collection><collection>China Online Journals (COJ)</collection><jtitle>Journal of control theory and applications</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Yin, Gang</au><au>Wang, Le Yi</au><au>Sun, Yu</au><au>Casbeer, David</au><au>Holsapple, Raymond</au><au>Kingston, Derek</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Asymptotic optimality for consensus-type stochastic approximation algorithms using iterate averaging</atitle><jtitle>Journal of control theory and applications</jtitle><stitle>J. Control Theory Appl</stitle><addtitle>Journal of Control Theory and Applications</addtitle><date>2013-02-01</date><risdate>2013</risdate><volume>11</volume><issue>1</issue><spage>1</spage><epage>9</epage><pages>1-9</pages><issn>1672-6340</issn><eissn>1993-0623</eissn><abstract>This paper introduces a post-iteration averaging algorithm to achieve asymptotic optimality in convergence rates of stochastic approximation algorithms for consensus control with structural constraints. The algorithm involves two stages. The first stage is a coarse approximation obtained using a sequence of large stepsizes. Then, the second stage provides a refinement by averaging the iterates from the first stage. We show that the new algorithm is asymptotically efficient and gives the optimal convergence rates in the sense of the best scaling factor and ＇smallest＇ possible asymptotic variance.</abstract><cop>Heidelberg</cop><pub>South China University of Technology and Academy of Mathematics and Systems Science, CAS</pub><doi>10.1007/s11768-013-2013-2</doi><tpages>9</tpages></addata></record>
fulltext fulltext
identifier ISSN: 1672-6340
ispartof Journal of control theory and applications, 2013-02, Vol.11 (1), p.1-9
issn 1672-6340
1993-0623
language eng
recordid cdi_wanfang_journals_kzllyyy_e201301001
source Springer Nature
subjects Algorithms
Approximation
Asymptotic properties
Complexity
Computational Intelligence
Control
Control and Systems Theory
Control theory
Convergence
Engineering
Mathematical analysis
Mechatronics
Optimization
Robotics
Stochasticity
Systems Theory
平均
最优收敛速度
渐近方差
渐近最优
渐近有效
近似算法
迭代点
随机逼近算法
title Asymptotic optimality for consensus-type stochastic approximation algorithms using iterate averaging
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-27T09%3A07%3A52IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-wanfang_jour_proqu&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Asymptotic%20optimality%20for%20consensus-type%20stochastic%20approximation%20algorithms%20using%20iterate%20averaging&rft.jtitle=Journal%20of%20control%20theory%20and%20applications&rft.au=Yin,%20Gang&rft.date=2013-02-01&rft.volume=11&rft.issue=1&rft.spage=1&rft.epage=9&rft.pages=1-9&rft.issn=1672-6340&rft.eissn=1993-0623&rft_id=info:doi/10.1007/s11768-013-2013-2&rft_dat=%3Cwanfang_jour_proqu%3Ekzllyyy_e201301001%3C/wanfang_jour_proqu%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c2971-db69b2d8c8547b71ee9cfd4a5b653659da0041eba3f43965c0cc4941825a9f583%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=1671421443&rft_id=info:pmid/&rft_cqvip_id=44519257&rft_wanfj_id=kzllyyy_e201301001&rfr_iscdi=true