Robustness and Convergence Analysis of First-Order Distributed Optimization Algorithms over Subspace Constraints

Robustness and Convergence Analysis of First-Order Distributed Optimization Algorithms over Subspace Constraints

This paper extends algorithms that remove the fixed point bias of decentralized gradient descent to solve the more general problem of distributed optimization over subspace constraints. Leveraging the integral quadratic constraint framework, we analyze the performance of these generalized algorithms...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Marquis, Dennis J, Jaoude, Dany Abou, Farhood, Mazen, Woolsey, Craig A
Format: Artikel
Sprache:eng
Schlagworte:
Mathematics - Optimization and Control
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator Marquis, Dennis J
Jaoude, Dany Abou
Farhood, Mazen
Woolsey, Craig A
description This paper extends algorithms that remove the fixed point bias of decentralized gradient descent to solve the more general problem of distributed optimization over subspace constraints. Leveraging the integral quadratic constraint framework, we analyze the performance of these generalized algorithms in terms of worst-case robustness and convergence rate. The utility of our framework is demonstrated by showing how one of the extended algorithms, originally designed for consensus, is now able to solve a multitask inference problem.
doi_str_mv 10.48550/arxiv.2210.16277
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2210_16277</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2210_16277</sourcerecordid><originalsourceid>FETCH-LOGICAL-a677-2512eaa2dd90cf8ba315f57283fc7b813fd3441e394aa8852ca12e50d999b1323</originalsourceid><addsrcrecordid>eNotj9FKwzAYRnPjhUwfwCvzAp1N0izpZalOhcFAd1_-NMkMtGlJ0uF8euPc1QcfnAMHoQdSrivJefkE4dud1pTmg2yoELdo_pjUEpM3MWLwGreTP5lwNL43uPEwnKOLeLJ460JMxT5oE_Cziyk4tSSj8X5ObnQ_kNzkcTMcp-DS15iRbMGfi4ozZFO2ZgScT_EO3VgYorm_7godti-H9q3Y7V_f22ZXwEaIgnJCDQDVui57KxUwwi0XVDLbCyUJs5pVFTGsrgCk5LSHDPBS13WtCKNshR7_tZfkbg5uhHDu_tK7Szr7BcwcVmw</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Robustness and Convergence Analysis of First-Order Distributed Optimization Algorithms over Subspace Constraints</title><source>arXiv.org</source><creator>Marquis, Dennis J ; Jaoude, Dany Abou ; Farhood, Mazen ; Woolsey, Craig A</creator><creatorcontrib>Marquis, Dennis J ; Jaoude, Dany Abou ; Farhood, Mazen ; Woolsey, Craig A</creatorcontrib><description>This paper extends algorithms that remove the fixed point bias of decentralized gradient descent to solve the more general problem of distributed optimization over subspace constraints. Leveraging the integral quadratic constraint framework, we analyze the performance of these generalized algorithms in terms of worst-case robustness and convergence rate. The utility of our framework is demonstrated by showing how one of the extended algorithms, originally designed for consensus, is now able to solve a multitask inference problem.</description><identifier>DOI: 10.48550/arxiv.2210.16277</identifier><language>eng</language><subject>Mathematics - Optimization and Control</subject><creationdate>2022-10</creationdate><rights>http://creativecommons.org/licenses/by/4.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,776,881</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2210.16277$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2210.16277$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Marquis, Dennis J</creatorcontrib><creatorcontrib>Jaoude, Dany Abou</creatorcontrib><creatorcontrib>Farhood, Mazen</creatorcontrib><creatorcontrib>Woolsey, Craig A</creatorcontrib><title>Robustness and Convergence Analysis of First-Order Distributed Optimization Algorithms over Subspace Constraints</title><description>This paper extends algorithms that remove the fixed point bias of decentralized gradient descent to solve the more general problem of distributed optimization over subspace constraints. Leveraging the integral quadratic constraint framework, we analyze the performance of these generalized algorithms in terms of worst-case robustness and convergence rate. The utility of our framework is demonstrated by showing how one of the extended algorithms, originally designed for consensus, is now able to solve a multitask inference problem.</description><subject>Mathematics - Optimization and Control</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotj9FKwzAYRnPjhUwfwCvzAp1N0izpZalOhcFAd1_-NMkMtGlJ0uF8euPc1QcfnAMHoQdSrivJefkE4dud1pTmg2yoELdo_pjUEpM3MWLwGreTP5lwNL43uPEwnKOLeLJ460JMxT5oE_Cziyk4tSSj8X5ObnQ_kNzkcTMcp-DS15iRbMGfi4ozZFO2ZgScT_EO3VgYorm_7godti-H9q3Y7V_f22ZXwEaIgnJCDQDVui57KxUwwi0XVDLbCyUJs5pVFTGsrgCk5LSHDPBS13WtCKNshR7_tZfkbg5uhHDu_tK7Szr7BcwcVmw</recordid><startdate>20221028</startdate><enddate>20221028</enddate><creator>Marquis, Dennis J</creator><creator>Jaoude, Dany Abou</creator><creator>Farhood, Mazen</creator><creator>Woolsey, Craig A</creator><scope>AKZ</scope><scope>GOX</scope></search><sort><creationdate>20221028</creationdate><title>Robustness and Convergence Analysis of First-Order Distributed Optimization Algorithms over Subspace Constraints</title><author>Marquis, Dennis J ; Jaoude, Dany Abou ; Farhood, Mazen ; Woolsey, Craig A</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a677-2512eaa2dd90cf8ba315f57283fc7b813fd3441e394aa8852ca12e50d999b1323</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Mathematics - Optimization and Control</topic><toplevel>online_resources</toplevel><creatorcontrib>Marquis, Dennis J</creatorcontrib><creatorcontrib>Jaoude, Dany Abou</creatorcontrib><creatorcontrib>Farhood, Mazen</creatorcontrib><creatorcontrib>Woolsey, Craig A</creatorcontrib><collection>arXiv Mathematics</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Marquis, Dennis J</au><au>Jaoude, Dany Abou</au><au>Farhood, Mazen</au><au>Woolsey, Craig A</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Robustness and Convergence Analysis of First-Order Distributed Optimization Algorithms over Subspace Constraints</atitle><date>2022-10-28</date><risdate>2022</risdate><abstract>This paper extends algorithms that remove the fixed point bias of decentralized gradient descent to solve the more general problem of distributed optimization over subspace constraints. Leveraging the integral quadratic constraint framework, we analyze the performance of these generalized algorithms in terms of worst-case robustness and convergence rate. The utility of our framework is demonstrated by showing how one of the extended algorithms, originally designed for consensus, is now able to solve a multitask inference problem.</abstract><doi>10.48550/arxiv.2210.16277</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2210.16277
ispartof
issn
language eng
recordid cdi_arxiv_primary_2210_16277
source arXiv.org
subjects Mathematics - Optimization and Control
title Robustness and Convergence Analysis of First-Order Distributed Optimization Algorithms over Subspace Constraints
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-09T01%3A34%3A13IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Robustness%20and%20Convergence%20Analysis%20of%20First-Order%20Distributed%20Optimization%20Algorithms%20over%20Subspace%20Constraints&rft.au=Marquis,%20Dennis%20J&rft.date=2022-10-28&rft_id=info:doi/10.48550/arxiv.2210.16277&rft_dat=%3Carxiv_GOX%3E2210_16277%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true