A new composite gradient algorithm to achieve global convergence
Insufficient-order system identification can result in a multimodal mean square error surface on which a gradient-type algorithm may converge to a local minimum. In this letter a new composite gradient algorithm (CGA) is presented which is due to achieve global convergence when the output error surf...
Gespeichert in:
| Veröffentlicht in: | IEEE transactions on circuits and systems. 2, Analog and digital signal processing Analog and digital signal processing, 1995-10, Vol.42 (10), p.681-684 |
|---|---|
| Hauptverfasser: | , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 684 |
|---|---|
| container_issue | 10 |
| container_start_page | 681 |
| container_title | IEEE transactions on circuits and systems. 2, Analog and digital signal processing |
| container_volume | 42 |
| creator | Simon, G. Peceli, G. |
| description | Insufficient-order system identification can result in a multimodal mean square error surface on which a gradient-type algorithm may converge to a local minimum. In this letter a new composite gradient algorithm (CGA) is presented which is due to achieve global convergence when the output error surface contains local minima. The proposed algorithm combines the useful properties of the output error (OE) and equation error (EE) adaptive filtering methods using a new dynamic error surface. The CGA provides a single convergence point for the gradient-search algorithm independently of the initial conditions. The "global convergence" conjecture is illustrated by simulation examples showing good global convergence properties even in such undermodeled cases when the Steiglitz-McBride algorithm fails.< > |
| doi_str_mv | 10.1109/82.471398 |
| format | Article |
| fullrecord | <record><control><sourceid>pascalfrancis_RIE</sourceid><recordid>TN_cdi_crossref_primary_10_1109_82_471398</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>471398</ieee_id><sourcerecordid>2902306</sourcerecordid><originalsourceid>FETCH-LOGICAL-c275t-64db81bbb6fa2c7c64783ba92352d62f7fede60b7f7314b3f791cdcc40bcb6573</originalsourceid><addsrcrecordid>eNo9j0tLw0AUhQdRsFYXbl1l4cZF6jwyj-wspT6g4EbBXZi5uZOOpEmZCRX_vZGUru6F7zsHDiG3jC4Yo-Wj4YtCM1GaMzJjUpqccfl1Pv5U6nwE9JJcpfRNKTWsNDPytMw6_Mmg3-37FAbMmmjrgN2Q2bbpYxi2u2zoMwvbgIeRtr2z7ah3B4wNdoDX5MLbNuHN8c7J5_P6Y_Wab95f3lbLTQ5cyyFXRe0Mc84pbzloUIU2wtmSC8lrxb32WKOiTnstWOGE1yWDGqCgDpySWszJw9QLsU8poq_2Mexs_K0Yrf6nV4ZX0_TRvZ_cvU1gWx9tByGdArykXFA1aneTFhDxRI8df4h0YRE</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>A new composite gradient algorithm to achieve global convergence</title><source>IEEE Electronic Library (IEL)</source><creator>Simon, G. ; Peceli, G.</creator><creatorcontrib>Simon, G. ; Peceli, G.</creatorcontrib><description>Insufficient-order system identification can result in a multimodal mean square error surface on which a gradient-type algorithm may converge to a local minimum. In this letter a new composite gradient algorithm (CGA) is presented which is due to achieve global convergence when the output error surface contains local minima. The proposed algorithm combines the useful properties of the output error (OE) and equation error (EE) adaptive filtering methods using a new dynamic error surface. The CGA provides a single convergence point for the gradient-search algorithm independently of the initial conditions. The "global convergence" conjecture is illustrated by simulation examples showing good global convergence properties even in such undermodeled cases when the Steiglitz-McBride algorithm fails.< ></description><identifier>ISSN: 1057-7130</identifier><identifier>EISSN: 1558-125X</identifier><identifier>DOI: 10.1109/82.471398</identifier><identifier>CODEN: ICSPE5</identifier><language>eng</language><publisher>New York, NY: IEEE</publisher><subject>Applied sciences ; Convergence ; Detection, estimation, filtering, equalization, prediction ; Equations ; Exact sciences and technology ; Filtering algorithms ; Information, signal and communications theory ; Mean square error methods ; Operational amplifiers ; Predictive models ; Semiconductor device modeling ; Signal and communications theory ; Signal processing algorithms ; Signal, noise ; Solid state circuits ; Strontium ; Telecommunications and information theory</subject><ispartof>IEEE transactions on circuits and systems. 2, Analog and digital signal processing, 1995-10, Vol.42 (10), p.681-684</ispartof><rights>1996 INIST-CNRS</rights><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c275t-64db81bbb6fa2c7c64783ba92352d62f7fede60b7f7314b3f791cdcc40bcb6573</citedby><cites>FETCH-LOGICAL-c275t-64db81bbb6fa2c7c64783ba92352d62f7fede60b7f7314b3f791cdcc40bcb6573</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/471398$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>314,776,780,792,27903,27904,54737</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/471398$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc><backlink>$$Uhttp://pascal-francis.inist.fr/vibad/index.php?action=getRecordDetail&idt=2902306$$DView record in Pascal Francis$$Hfree_for_read</backlink></links><search><creatorcontrib>Simon, G.</creatorcontrib><creatorcontrib>Peceli, G.</creatorcontrib><title>A new composite gradient algorithm to achieve global convergence</title><title>IEEE transactions on circuits and systems. 2, Analog and digital signal processing</title><addtitle>T-CAS2</addtitle><description>Insufficient-order system identification can result in a multimodal mean square error surface on which a gradient-type algorithm may converge to a local minimum. In this letter a new composite gradient algorithm (CGA) is presented which is due to achieve global convergence when the output error surface contains local minima. The proposed algorithm combines the useful properties of the output error (OE) and equation error (EE) adaptive filtering methods using a new dynamic error surface. The CGA provides a single convergence point for the gradient-search algorithm independently of the initial conditions. The "global convergence" conjecture is illustrated by simulation examples showing good global convergence properties even in such undermodeled cases when the Steiglitz-McBride algorithm fails.< ></description><subject>Applied sciences</subject><subject>Convergence</subject><subject>Detection, estimation, filtering, equalization, prediction</subject><subject>Equations</subject><subject>Exact sciences and technology</subject><subject>Filtering algorithms</subject><subject>Information, signal and communications theory</subject><subject>Mean square error methods</subject><subject>Operational amplifiers</subject><subject>Predictive models</subject><subject>Semiconductor device modeling</subject><subject>Signal and communications theory</subject><subject>Signal processing algorithms</subject><subject>Signal, noise</subject><subject>Solid state circuits</subject><subject>Strontium</subject><subject>Telecommunications and information theory</subject><issn>1057-7130</issn><issn>1558-125X</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>1995</creationdate><recordtype>article</recordtype><recordid>eNo9j0tLw0AUhQdRsFYXbl1l4cZF6jwyj-wspT6g4EbBXZi5uZOOpEmZCRX_vZGUru6F7zsHDiG3jC4Yo-Wj4YtCM1GaMzJjUpqccfl1Pv5U6nwE9JJcpfRNKTWsNDPytMw6_Mmg3-37FAbMmmjrgN2Q2bbpYxi2u2zoMwvbgIeRtr2z7ah3B4wNdoDX5MLbNuHN8c7J5_P6Y_Wab95f3lbLTQ5cyyFXRe0Mc84pbzloUIU2wtmSC8lrxb32WKOiTnstWOGE1yWDGqCgDpySWszJw9QLsU8poq_2Mexs_K0Yrf6nV4ZX0_TRvZ_cvU1gWx9tByGdArykXFA1aneTFhDxRI8df4h0YRE</recordid><startdate>19951001</startdate><enddate>19951001</enddate><creator>Simon, G.</creator><creator>Peceli, G.</creator><general>IEEE</general><general>Institute of Electrical and Electronics Engineers</general><scope>IQODW</scope><scope>AAYXX</scope><scope>CITATION</scope></search><sort><creationdate>19951001</creationdate><title>A new composite gradient algorithm to achieve global convergence</title><author>Simon, G. ; Peceli, G.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c275t-64db81bbb6fa2c7c64783ba92352d62f7fede60b7f7314b3f791cdcc40bcb6573</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>1995</creationdate><topic>Applied sciences</topic><topic>Convergence</topic><topic>Detection, estimation, filtering, equalization, prediction</topic><topic>Equations</topic><topic>Exact sciences and technology</topic><topic>Filtering algorithms</topic><topic>Information, signal and communications theory</topic><topic>Mean square error methods</topic><topic>Operational amplifiers</topic><topic>Predictive models</topic><topic>Semiconductor device modeling</topic><topic>Signal and communications theory</topic><topic>Signal processing algorithms</topic><topic>Signal, noise</topic><topic>Solid state circuits</topic><topic>Strontium</topic><topic>Telecommunications and information theory</topic><toplevel>online_resources</toplevel><creatorcontrib>Simon, G.</creatorcontrib><creatorcontrib>Peceli, G.</creatorcontrib><collection>Pascal-Francis</collection><collection>CrossRef</collection><jtitle>IEEE transactions on circuits and systems. 2, Analog and digital signal processing</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Simon, G.</au><au>Peceli, G.</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>A new composite gradient algorithm to achieve global convergence</atitle><jtitle>IEEE transactions on circuits and systems. 2, Analog and digital signal processing</jtitle><stitle>T-CAS2</stitle><date>1995-10-01</date><risdate>1995</risdate><volume>42</volume><issue>10</issue><spage>681</spage><epage>684</epage><pages>681-684</pages><issn>1057-7130</issn><eissn>1558-125X</eissn><coden>ICSPE5</coden><abstract>Insufficient-order system identification can result in a multimodal mean square error surface on which a gradient-type algorithm may converge to a local minimum. In this letter a new composite gradient algorithm (CGA) is presented which is due to achieve global convergence when the output error surface contains local minima. The proposed algorithm combines the useful properties of the output error (OE) and equation error (EE) adaptive filtering methods using a new dynamic error surface. The CGA provides a single convergence point for the gradient-search algorithm independently of the initial conditions. The "global convergence" conjecture is illustrated by simulation examples showing good global convergence properties even in such undermodeled cases when the Steiglitz-McBride algorithm fails.< ></abstract><cop>New York, NY</cop><pub>IEEE</pub><doi>10.1109/82.471398</doi><tpages>4</tpages></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISSN: 1057-7130 |
| ispartof | IEEE transactions on circuits and systems. 2, Analog and digital signal processing, 1995-10, Vol.42 (10), p.681-684 |
| issn | 1057-7130 1558-125X |
| language | eng |
| recordid | cdi_crossref_primary_10_1109_82_471398 |
| source | IEEE Electronic Library (IEL) |
| subjects | Applied sciences Convergence Detection, estimation, filtering, equalization, prediction Equations Exact sciences and technology Filtering algorithms Information, signal and communications theory Mean square error methods Operational amplifiers Predictive models Semiconductor device modeling Signal and communications theory Signal processing algorithms Signal, noise Solid state circuits Strontium Telecommunications and information theory |
| title | A new composite gradient algorithm to achieve global convergence |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-23T00%3A27%3A27IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-pascalfrancis_RIE&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=A%20new%20composite%20gradient%20algorithm%20to%20achieve%20global%20convergence&rft.jtitle=IEEE%20transactions%20on%20circuits%20and%20systems.%202,%20Analog%20and%20digital%20signal%20processing&rft.au=Simon,%20G.&rft.date=1995-10-01&rft.volume=42&rft.issue=10&rft.spage=681&rft.epage=684&rft.pages=681-684&rft.issn=1057-7130&rft.eissn=1558-125X&rft.coden=ICSPE5&rft_id=info:doi/10.1109/82.471398&rft_dat=%3Cpascalfrancis_RIE%3E2902306%3C/pascalfrancis_RIE%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=471398&rfr_iscdi=true |