Monotonic convergence of fixed-point algorithms for ICA

We re-examine a fixed-point algorithm proposed by Hyvarinen for independent component analysis, wherein local convergence is proved subject to an ideal signal model using a square invertible mixing matrix. Here, we derive step-size bounds which ensure monotonic convergence to a local extremum for an...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	IEEE transactions on neural networks Ročník 14; číslo 4; s. 943 - 949
Hlavní autoři:	Regalia, P.A., Kofidis, E.
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	United States IEEE 01.07.2003 Institute of Electrical and Electronics Engineers
Témata:	Algorithms Appeals Background noise Convergence Engineering Sciences Fixed points (mathematics) Image restoration Independent component analysis Information processing Initial conditions Mathematical models Neural networks Probability density function Random variables Sensors Signal analysis Signal and Image processing Signal restoration Vectors Non-Gaussian signals Fixed-point algorithms Monotonic convergence Independent component analysis (ICA)
ISSN:	1045-9227
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Abstract	We re-examine a fixed-point algorithm proposed by Hyvarinen for independent component analysis, wherein local convergence is proved subject to an ideal signal model using a square invertible mixing matrix. Here, we derive step-size bounds which ensure monotonic convergence to a local extremum for any initial condition. Our analysis does not assume an ideal signal model but appeals rather to properties of the contrast function itself, and so applies even with noisy data and/or more sources than sensors. The results help alleviate the guesswork that often surrounds step-size selection when the observed signal does not fit an idealized model.
AbstractList	We re-examine a fixed-point algorithm proposed by Hyvarinen for independent component analysis, wherein local convergence is proved subject to an ideal signal model using a square invertible mixing matrix. Here, we derive step-size bounds which ensure monotonic convergence to a local extremum for any initial condition. Our analysis does not assume an ideal signal model but appeals rather to properties of the contrast function itself, and so applies even with noisy data and/or more sources than sensors. The results help alleviate the guesswork that often surrounds step-size selection when the observed signal does not fit an idealized model We re-examine a fixed-point algorithm proposed by Hyvarinen for independent component analysis, wherein local convergence is proved subject to an ideal signal model using a square invertible mixing matrix. Here, we derive step-size bounds which ensure monotonic convergence to a local extremum for any initial condition. Our analysis does not assume an ideal signal model but appeals rather to properties of the contrast function itself, and so applies even with noisy data and/or more sources than sensors. The results help alleviate the guesswork that often surrounds step-size selection when the observed signal does not fit an idealized model. We re-examine a fixed-point algorithm proposed by Hyvarinen for independent component analysis, wherein local convergence is proved subject to an ideal signal model using a square invertible mixing matrix. Here, we derive step-size bounds which ensure monotonic convergence to a local extremum for any initial condition. Our analysis does not assume an ideal signal model but appeals rather to properties of the contrast function itself, and so applies even with noisy data and/or more sources than sensors. The results help alleviate the guesswork that often surrounds step-size selection when the observed signal does not fit an idealized model.We re-examine a fixed-point algorithm proposed by Hyvarinen for independent component analysis, wherein local convergence is proved subject to an ideal signal model using a square invertible mixing matrix. Here, we derive step-size bounds which ensure monotonic convergence to a local extremum for any initial condition. Our analysis does not assume an ideal signal model but appeals rather to properties of the contrast function itself, and so applies even with noisy data and/or more sources than sensors. The results help alleviate the guesswork that often surrounds step-size selection when the observed signal does not fit an idealized model.
Author	Regalia, P.A. Kofidis, E.
Author_xml	– sequence: 1 givenname: P.A. surname: Regalia fullname: Regalia, P.A. organization: Dept. of Commun., Image, & Inf. processing, Inst. Nat. des Telecommun., Evry, France – sequence: 2 givenname: E. surname: Kofidis fullname: Kofidis, E.
BackLink	https://www.ncbi.nlm.nih.gov/pubmed/18238073$$D View this record in MEDLINE/PubMed https://hal.science/hal-01345079$$DView record in HAL
BookMark	eNqF0c1PHCEYBnAONn723INJM6eaHmYFXmaAozG2NtnqRc-EYV4UMwtbmN3of9_ZjK1JD_ZEAr-Hr-eI7MUUkZBPjC4Yo_r87uZmwSmFhWKgBOyRQ0ZFU2vO5QE5KuWJUiYa2u6TA6Y4KCrhkMifKaYxxeAql-IW8wNGh1XylQ_P2NfrFOJY2eEh5TA-rkrlU65-XF6ckA_eDgU_vo7H5P7b1d3ldb28_T4tL2snQI21B66Y6NB3qJ1jUndgpXcoLROOg9cIjRCacoEt9LJV2nvQvm-Y8qqjPRyTr_O-j3Yw6xxWNr-YZIO5vlia3RxlMD1K6i2b7Nls1zn92mAZzSoUh8NgI6ZNMZqytpXt9EX_kxIEF1rInfzyruQKJFVcTPDzK9x0K-z_3vXPV0_gfAYup1Iy-jdCza5AMxVodgWaucAp0fyTcGG0Y0hxzDYM7-RO51xAxLdTOGsEo_AbnZOmaQ
CODEN	ITNNEP
CitedBy_id	crossref_primary_10_1109_TNN_2004_824258 crossref_primary_10_1109_TNN_2009_2035920 crossref_primary_10_1002_nla_2406 crossref_primary_10_1007_s40314_020_01182_y crossref_primary_10_1109_TNN_2007_908636 crossref_primary_10_1109_TSP_2015_2468686 crossref_primary_10_1007_s10107_015_0895_0 crossref_primary_10_1016_j_laa_2011_10_033 crossref_primary_10_1007_s11063_007_9037_x crossref_primary_10_1016_j_aca_2011_08_006 crossref_primary_10_1137_11085743X crossref_primary_10_1109_TSP_2009_2015114 crossref_primary_10_1002_nla_2031 crossref_primary_10_1109_TNN_2006_880980 crossref_primary_10_1007_s40305_016_0148_9 crossref_primary_10_1137_100801482 crossref_primary_10_1137_140951758 crossref_primary_10_1016_j_future_2004_11_024 crossref_primary_10_1016_j_dsp_2014_02_005 crossref_primary_10_1137_110835335 crossref_primary_10_1016_j_cam_2025_116716 crossref_primary_10_1016_j_sigpro_2007_08_014 crossref_primary_10_1007_s00521_015_2033_6 crossref_primary_10_1186_1687_6180_2014_151 crossref_primary_10_1109_TNN_2007_915117 crossref_primary_10_1109_TNN_2006_875991 crossref_primary_10_3390_e17085549 crossref_primary_10_1109_TSP_2006_870561
Cites_doi	10.1109/18.887889 10.1109/18.887862 10.1109/78.747781 10.1016/S0165-1684(98)00192-3 10.1515/9781400873173 10.1109/72.761722 10.1109/TAC.1980.1102343 10.1109/78.969518 10.1109/5.720246 10.1109/18.681326 10.1090/conm/280/04625 10.56021/9781421407944 10.1109/18.212280
ContentType	Journal Article
Copyright	Distributed under a Creative Commons Attribution 4.0 International License
Copyright_xml	– notice: Distributed under a Creative Commons Attribution 4.0 International License
DBID	RIA RIE AAYXX CITATION NPM 7SC 8FD JQ2 L7M L~C L~D 7X8 7SP F28 FR3 1XC
DOI	10.1109/TNN.2003.813843
DatabaseName	IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Electronic Library (IEL) CrossRef PubMed Computer and Information Systems Abstracts Technology Research Database ProQuest Computer Science Collection Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional MEDLINE - Academic Electronics & Communications Abstracts ANTE: Abstracts in New Technology & Engineering Engineering Research Database Hyper Article en Ligne (HAL)
DatabaseTitle	CrossRef PubMed Computer and Information Systems Abstracts Technology Research Database Computer and Information Systems Abstracts – Academic Advanced Technologies Database with Aerospace ProQuest Computer Science Collection Computer and Information Systems Abstracts Professional MEDLINE - Academic Electronics & Communications Abstracts Engineering Research Database ANTE: Abstracts in New Technology & Engineering
DatabaseTitleList	PubMed Technology Research Database Computer and Information Systems Abstracts MEDLINE - Academic
Database_xml	– sequence: 1 dbid: NPM name: PubMed url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 2 dbid: RIE name: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher – sequence: 3 dbid: 7X8 name: MEDLINE - Academic url: https://search.proquest.com/medline sourceTypes: Aggregation Database
DeliveryMethod	fulltext_linktorsrc
Discipline	Engineering Anatomy & Physiology Computer Science
EndPage	949
ExternalDocumentID	oai:HAL:hal-01345079v1 18238073 10_1109_TNN_2003_813843 1215410
Genre	Journal Article
GroupedDBID	--- -~X .DC 0R~ 29I 4.4 53G 5GY 5VS 6IK 97E AAJGR AASAJ AAWTH ABAZT ABJNI ABQJQ ABVLG ACGFS AETIX AGQYO AGSQL AHBIQ AI. AIBXA ALLEH ALMA_UNASSIGNED_HOLDINGS ASUFR ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 DU5 EBS EJD F5P HZ~ H~9 ICLAB IFIPE IFJZH IPLJI JAVBF LAI M43 MS~ O9- OCL P2P RIA RIE RNS S10 TAE TN5 VH1 AAYXX CITATION NPM RIG 7SC 8FD JQ2 L7M L~C L~D 7X8 7SP F28 FR3 1XC
ID	FETCH-LOGICAL-c438t-f32814befbe9cc179b3a7fce7a14c23f9e35449024e63d7689ff39fd518f8b0d3
IEDL.DBID	RIE
ISICitedReferencesCount	48
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000184371900019&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	1045-9227
IngestDate	Sun Oct 19 01:18:33 EDT 2025 Thu Sep 04 23:42:39 EDT 2025 Fri Sep 05 06:22:28 EDT 2025 Thu Sep 04 17:36:00 EDT 2025 Mon Jul 21 05:59:13 EDT 2025 Sat Nov 29 08:07:51 EST 2025 Tue Nov 18 22:13:15 EST 2025 Tue Aug 26 16:39:23 EDT 2025
IsPeerReviewed	false
IsScholarly	true
Issue	4
Keywords	Non-Gaussian signals Fixed-point algorithms Monotonic convergence Independent component analysis (ICA)
Language	English
License	https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html Distributed under a Creative Commons Attribution 4.0 International License: http://creativecommons.org/licenses/by/4.0
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c438t-f32814befbe9cc179b3a7fce7a14c23f9e35449024e63d7689ff39fd518f8b0d3
Notes	ObjectType-Article-2 SourceType-Scholarly Journals-1 ObjectType-Feature-1 content type line 23 ObjectType-Article-1 ObjectType-Feature-2
PMID	18238073
PQID	28370824
PQPubID	23500
PageCount	7
ParticipantIDs	proquest_miscellaneous_901667600 ieee_primary_1215410 pubmed_primary_18238073 crossref_citationtrail_10_1109_TNN_2003_813843 hal_primary_oai_HAL_hal_01345079v1 proquest_miscellaneous_28370824 crossref_primary_10_1109_TNN_2003_813843 proquest_miscellaneous_734249470
PublicationCentury	2000
PublicationDate	2003-07-01
PublicationDateYYYYMMDD	2003-07-01
PublicationDate_xml	– month: 07 year: 2003 text: 2003-07-01 day: 01
PublicationDecade	2000
PublicationPlace	United States
PublicationPlace_xml	– name: United States
PublicationTitle	IEEE transactions on neural networks
PublicationTitleAbbrev	TNN
PublicationTitleAlternate	IEEE Trans Neural Netw
PublicationYear	2003
Publisher	IEEE Institute of Electrical and Electronics Engineers
Publisher_xml	– name: IEEE – name: Institute of Electrical and Electronics Engineers
References	ref13 ref12 ref15 ref14 ref11 ref10 ref2 ref8 ref7 Hyvärinen (ref1) 1999; 2 ref4 ref3 ref6 ref5 Delathauwer (ref9)
References_xml	– ident: ref11 doi: 10.1109/18.887889 – ident: ref7 doi: 10.1109/18.887862 – volume: 2 start-page: 94 year: 1999 ident: ref1 article-title: Survey on independent component analysis publication-title: Neural Comput. Surveys – ident: ref5 doi: 10.1109/78.747781 – ident: ref8 doi: 10.1016/S0165-1684(98)00192-3 – ident: ref14 doi: 10.1515/9781400873173 – volume-title: Proc. NOLTA ident: ref9 article-title: The higher order power method: Application in independent component analysis – ident: ref2 doi: 10.1109/72.761722 – ident: ref13 doi: 10.1109/TAC.1980.1102343 – ident: ref3 doi: 10.1109/78.969518 – ident: ref4 doi: 10.1109/5.720246 – ident: ref6 doi: 10.1109/18.681326 – ident: ref10 doi: 10.1090/conm/280/04625 – ident: ref15 doi: 10.56021/9781421407944 – ident: ref12 doi: 10.1109/18.212280
SSID	ssj0014506
Score	1.9636862
Snippet	We re-examine a fixed-point algorithm proposed by Hyvarinen for independent component analysis, wherein local convergence is proved subject to an ideal signal...
SourceID	hal proquest pubmed crossref ieee
SourceType	Open Access Repository Aggregation Database Index Database Enrichment Source Publisher
StartPage	943
SubjectTerms	Algorithms Appeals Background noise Convergence Engineering Sciences Fixed points (mathematics) Image restoration Independent component analysis Information processing Initial conditions Mathematical models Neural networks Probability density function Random variables Sensors Signal analysis Signal and Image processing Signal restoration Vectors
Title	Monotonic convergence of fixed-point algorithms for ICA
URI	https://ieeexplore.ieee.org/document/1215410 https://www.ncbi.nlm.nih.gov/pubmed/18238073 https://www.proquest.com/docview/28370824 https://www.proquest.com/docview/734249470 https://www.proquest.com/docview/901667600 https://hal.science/hal-01345079
Volume	14
WOSCitedRecordID	wos000184371900019&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText	1
inHoldings	1
isFullTextHit
isPrint
journalDatabaseRights	– providerCode: PRVIEE databaseName: IEEE Electronic Library (IEL) issn: 1045-9227 databaseCode: RIE dateStart: 19900101 customDbUrl: isFulltext: true dateEnd: 20111231 titleUrlDefault: https://ieeexplore.ieee.org/ omitProxy: false ssIdentifier: ssj0014506 providerName: IEEE
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1La9wwEB6S0EN7aNrdPtxHKkopPdQbW5It6biEhhTC0kMKezO2PGoWEjvsekPz7zOSvZsWuofejBnbwjOD5tPMfAPwydOc8ZK7uLQlj6VUeexbe2KeC1c7IxPbTy05V7OZns_Njz34uu2FQcRQfIYTfxly-XVr1_6o7NgzIUjfT7WvVN73am0zBjILczQJXWSx4VwNND5pYo4vZrNA_DnRqdBS_LUD7V_6-scwWGV3jBn2mtPD_1vlM3g6xJRs2hvBc9jDZgTjaUN4-vqOfWahyjMcn4_gcDPGgQ1ePYInf3ASjkGRl7edJ8xloSI9NGciax1zi99YxzftoulYefWrXS66y-sVo6iXfT-ZvoCfp98uTs7iYbpCbKXQXewE16ms0FVorCW_rESpnEVVptJy4QyKTEpDezjmoiZUYpwTxtVZqp2uklq8hIOmbfA1sDTDHAnnyUon0qHSjj6RyZLgZF1hwiOYbP54YQfqcT8B46oIECQxBanID8QURa-iCL5sH7jpWTd2i34kFW6lPFv22fS88PcouiWrUOY2jWDs9fTwrl5FEXzYaLwgr_KpkrLBdr0qAieQ5jICtkNCCUnIVapktwiFWr6COCGRV705PSxAc8_0L978e2Fv4XEoGgxlwe_goFuu8T08srfdYrU8IvOf66Ng_vc7AP35
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3fb9MwED6NgQR7YNACC79mIYR4IJ1jO7X9WE1MnSgRD0XaW5Q4Nqu0JVObTvDfc3bSDiT6wFsUXRLL55Pv4u--D-C9pzljBXNxYQoWCyHHsW_tidmYu8ppQU2nWjKTWaYuLvS3Pfi07YWx1gbwmR35y3CWXzVm7X-VnXgmBOH7qe6nQjDadWttzwxEGpQ0sb5IY82Y7Il8EqpP5lkWqD9HKuFK8L_2oHuXHgEZpFV2Z5lhtzk7_L9xPoHHfVZJJt0yeAp7th7AcFJjRX39i3wgAecZfqAP4HAj5ED6uB7AwR-shEOQGOdN6ylzScCkh_ZMSxpH3OKnreKbZlG3pLj60SwX7eX1imDeS85PJ8_g-9nn-ek07vUVYiO4amPHmUpEaV1ptTEYmSUvpDNWFokwjDttOc6zxl3cjnmFdYl2jmtXpYlyqqQVfw77dVPbIyBJascWKz1RKiqclcrhJ1JRYEFZlZayCEabGc9NTz7uNTCu8lCEUJ2ji7wkJs87F0XwcfvATce7sdv0Hbpwa-X5sqeTWe7vYX6Lq0Lq2ySCoffT3bs6F0VwvPF4jnHlD0uK2jbrVR5YgRQTEZAdFpILrF2FpLtNMNnyGGKKJi-65XQ3AMU81z9_-e-BHcPD6fzrLJ-dZ19ewaMAIQwg4dew3y7X9g08MLftYrV8G4LgN5V_AGc
openUrl	ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Monotonic+convergence+of+fixed-point+algorithms+for+ICA&rft.jtitle=IEEE+transactions+on+neural+networks&rft.au=Regalia%2C+P+A&rft.au=Kofidis%2C+E&rft.date=2003-07-01&rft.issn=1045-9227&rft.volume=14&rft.issue=4&rft.spage=943&rft.epage=949&rft_id=info:doi/10.1109%2FTNN.2003.813843&rft.externalDBID=NO_FULL_TEXT
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1045-9227&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1045-9227&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1045-9227&client=summon