A projected stochastic approximation algorithm
It is noted that classical stochastic approximation algorithms often diverge because of boundedness problems. The standard approach to preventing this is to project the sequence generated by the algorithm onto a predetermined compact set K. However, in the typical application, the approximate locati...
Gespeichert in:
| 1. Verfasser: | |
|---|---|
| Format: | Tagungsbericht |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 957 |
|---|---|
| container_issue | |
| container_start_page | 954 |
| container_title | |
| container_volume | |
| creator | Andradottir, S. |
| description | It is noted that classical stochastic approximation algorithms often diverge because of boundedness problems. The standard approach to preventing this is to project the sequence generated by the algorithm onto a predetermined compact set K. However, in the typical application, the approximate location of the solution is not known. To minimize the probability that the solution lies outside the set K, it is therefore necessary to let K be large. This can seriously curtail the efficiency of the algorithm. The author proposes a stochastic approximation algorithm which bounds the sequence of estimates of the solution to an increasing sequence of sets. This eliminates the possibility of bounding the algorithm to a set which does not contain the solution. Furthermore, it is possible to let the initial set be small, which can result in improved empirical performance.< > |
| doi_str_mv | 10.1109/WSC.1991.185710 |
| format | Conference Proceeding |
| fullrecord | <record><control><sourceid>ieee_6IE</sourceid><recordid>TN_cdi_ieee_primary_185710</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>185710</ieee_id><sourcerecordid>185710</sourcerecordid><originalsourceid>FETCH-LOGICAL-i145t-acd861118d78fcab2368adfbfef9a5997ad88f5098fb21e5819ffa0b99620ca53</originalsourceid><addsrcrecordid>eNotj0tLxEAQhAdEUNacBU_5A4ndmZ2k-7gEX7DgQcXj0pmHO8uuCZk56L83sBYFBd-hqFLqFqFGBL7_fOtrZMYayXQIF6rgjmCxBiSkK1WkdIBFa91q1Neq3pTTPB68zd6VKY92LylHW8q04J94khzH71KOX-Mc8_50oy6DHJMv_nOlPh4f3vvnavv69NJvtlXEtcmVWEctIpLrKFgZGt2SuDAEH1gMcyeOKBhgCkOD3hByCAIDc9uAFaNX6u7cG733u2lehsy_u_Mp_QelY0JZ</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>A projected stochastic approximation algorithm</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Andradottir, S.</creator><creatorcontrib>Andradottir, S.</creatorcontrib><description>It is noted that classical stochastic approximation algorithms often diverge because of boundedness problems. The standard approach to preventing this is to project the sequence generated by the algorithm onto a predetermined compact set K. However, in the typical application, the approximate location of the solution is not known. To minimize the probability that the solution lies outside the set K, it is therefore necessary to let K be large. This can seriously curtail the efficiency of the algorithm. The author proposes a stochastic approximation algorithm which bounds the sequence of estimates of the solution to an increasing sequence of sets. This eliminates the possibility of bounding the algorithm to a set which does not contain the solution. Furthermore, it is possible to let the initial set be small, which can result in improved empirical performance.< ></description><identifier>ISBN: 9780780301818</identifier><identifier>ISBN: 0780301811</identifier><identifier>DOI: 10.1109/WSC.1991.185710</identifier><language>eng</language><publisher>IEEE</publisher><subject>Algorithm design and analysis ; Analytical models ; Approximation algorithms ; Convergence ; Finite difference methods ; H infinity control ; Industrial engineering ; Performance analysis ; Stochastic processes ; Stochastic systems</subject><ispartof>1991 Winter Simulation Conference Proceedings, 1991, p.954-957</ispartof><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/185710$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,780,784,789,790,2058,4050,4051,27925,54920</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/185710$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Andradottir, S.</creatorcontrib><title>A projected stochastic approximation algorithm</title><title>1991 Winter Simulation Conference Proceedings</title><addtitle>WSC</addtitle><description>It is noted that classical stochastic approximation algorithms often diverge because of boundedness problems. The standard approach to preventing this is to project the sequence generated by the algorithm onto a predetermined compact set K. However, in the typical application, the approximate location of the solution is not known. To minimize the probability that the solution lies outside the set K, it is therefore necessary to let K be large. This can seriously curtail the efficiency of the algorithm. The author proposes a stochastic approximation algorithm which bounds the sequence of estimates of the solution to an increasing sequence of sets. This eliminates the possibility of bounding the algorithm to a set which does not contain the solution. Furthermore, it is possible to let the initial set be small, which can result in improved empirical performance.< ></description><subject>Algorithm design and analysis</subject><subject>Analytical models</subject><subject>Approximation algorithms</subject><subject>Convergence</subject><subject>Finite difference methods</subject><subject>H infinity control</subject><subject>Industrial engineering</subject><subject>Performance analysis</subject><subject>Stochastic processes</subject><subject>Stochastic systems</subject><isbn>9780780301818</isbn><isbn>0780301811</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>1991</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><sourceid>RIE</sourceid><recordid>eNotj0tLxEAQhAdEUNacBU_5A4ndmZ2k-7gEX7DgQcXj0pmHO8uuCZk56L83sBYFBd-hqFLqFqFGBL7_fOtrZMYayXQIF6rgjmCxBiSkK1WkdIBFa91q1Neq3pTTPB68zd6VKY92LylHW8q04J94khzH71KOX-Mc8_50oy6DHJMv_nOlPh4f3vvnavv69NJvtlXEtcmVWEctIpLrKFgZGt2SuDAEH1gMcyeOKBhgCkOD3hByCAIDc9uAFaNX6u7cG733u2lehsy_u_Mp_QelY0JZ</recordid><startdate>1991</startdate><enddate>1991</enddate><creator>Andradottir, S.</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope></search><sort><creationdate>1991</creationdate><title>A projected stochastic approximation algorithm</title><author>Andradottir, S.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i145t-acd861118d78fcab2368adfbfef9a5997ad88f5098fb21e5819ffa0b99620ca53</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>1991</creationdate><topic>Algorithm design and analysis</topic><topic>Analytical models</topic><topic>Approximation algorithms</topic><topic>Convergence</topic><topic>Finite difference methods</topic><topic>H infinity control</topic><topic>Industrial engineering</topic><topic>Performance analysis</topic><topic>Stochastic processes</topic><topic>Stochastic systems</topic><toplevel>online_resources</toplevel><creatorcontrib>Andradottir, S.</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>Andradottir, S.</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>A projected stochastic approximation algorithm</atitle><btitle>1991 Winter Simulation Conference Proceedings</btitle><stitle>WSC</stitle><date>1991</date><risdate>1991</risdate><spage>954</spage><epage>957</epage><pages>954-957</pages><isbn>9780780301818</isbn><isbn>0780301811</isbn><abstract>It is noted that classical stochastic approximation algorithms often diverge because of boundedness problems. The standard approach to preventing this is to project the sequence generated by the algorithm onto a predetermined compact set K. However, in the typical application, the approximate location of the solution is not known. To minimize the probability that the solution lies outside the set K, it is therefore necessary to let K be large. This can seriously curtail the efficiency of the algorithm. The author proposes a stochastic approximation algorithm which bounds the sequence of estimates of the solution to an increasing sequence of sets. This eliminates the possibility of bounding the algorithm to a set which does not contain the solution. Furthermore, it is possible to let the initial set be small, which can result in improved empirical performance.< ></abstract><pub>IEEE</pub><doi>10.1109/WSC.1991.185710</doi><tpages>4</tpages><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISBN: 9780780301818 |
| ispartof | 1991 Winter Simulation Conference Proceedings, 1991, p.954-957 |
| issn | |
| language | eng |
| recordid | cdi_ieee_primary_185710 |
| source | IEEE Electronic Library (IEL) Conference Proceedings |
| subjects | Algorithm design and analysis Analytical models Approximation algorithms Convergence Finite difference methods H infinity control Industrial engineering Performance analysis Stochastic processes Stochastic systems |
| title | A projected stochastic approximation algorithm |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-05T06%3A50%3A43IST&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=A%20projected%20stochastic%20approximation%20algorithm&rft.btitle=1991%20Winter%20Simulation%20Conference%20Proceedings&rft.au=Andradottir,%20S.&rft.date=1991&rft.spage=954&rft.epage=957&rft.pages=954-957&rft.isbn=9780780301818&rft.isbn_list=0780301811&rft_id=info:doi/10.1109/WSC.1991.185710&rft_dat=%3Cieee_6IE%3E185710%3C/ieee_6IE%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=185710&rfr_iscdi=true |