Inverse Feasibility in Over-the-Air Federated Learning

Inverse Feasibility in Over-the-Air Federated Learning

We introduce the concept of inverse feasibility for linear forward models as a tool to enhance OTA FL algorithms. Inverse feasibility is defined as an upper bound on the condition number of the forward operator as a function of its parameters. We analyze an existing OTA FL model using this definitio...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:arXiv.org 2024-02
Hauptverfasser: Piotrowski, Tomasz, Ismayilov, Rafail, Frey, Matthias, Cavalcante, Renato L G
Format: Artikel
Sprache:eng
Schlagworte:
Federated learning
Iterative methods
Security
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title arXiv.org
container_volume
creator Piotrowski, Tomasz
Ismayilov, Rafail
Frey, Matthias
Cavalcante, Renato L G
description We introduce the concept of inverse feasibility for linear forward models as a tool to enhance OTA FL algorithms. Inverse feasibility is defined as an upper bound on the condition number of the forward operator as a function of its parameters. We analyze an existing OTA FL model using this definition, identify areas for improvement, and propose a new OTA FL model. Numerical experiments illustrate the main implications of the theoretical results. The proposed framework, which is based on inverse problem theory, can potentially complement existing notions of security and privacy by providing additional desirable characteristics to networks.
format Article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2741130372</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2741130372</sourcerecordid><originalsourceid>FETCH-proquest_journals_27411303723</originalsourceid><addsrcrecordid>eNpjYuA0MjY21LUwMTLiYOAtLs4yMDAwMjM3MjU15mQw88wrSy0qTlVwS00szkzKzMksqVTIzFPwB4rqlmSk6jpmFgHlUlKLEktSUxR8UhOL8jLz0nkYWNMSc4pTeaE0N4Oym2uIs4duQVF-YWlqcUl8Vn5pUR5QKt7I3MTQ0NjA2NzImDhVAJUrNMY</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2741130372</pqid></control><display><type>article</type><title>Inverse Feasibility in Over-the-Air Federated Learning</title><source>Freely Accessible Journals</source><creator>Piotrowski, Tomasz ; Ismayilov, Rafail ; Frey, Matthias ; Cavalcante, Renato L G</creator><creatorcontrib>Piotrowski, Tomasz ; Ismayilov, Rafail ; Frey, Matthias ; Cavalcante, Renato L G</creatorcontrib><description>We introduce the concept of inverse feasibility for linear forward models as a tool to enhance OTA FL algorithms. Inverse feasibility is defined as an upper bound on the condition number of the forward operator as a function of its parameters. We analyze an existing OTA FL model using this definition, identify areas for improvement, and propose a new OTA FL model. Numerical experiments illustrate the main implications of the theoretical results. The proposed framework, which is based on inverse problem theory, can potentially complement existing notions of security and privacy by providing additional desirable characteristics to networks.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Federated learning ; Iterative methods ; Security</subject><ispartof>arXiv.org, 2024-02</ispartof><rights>2024. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</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>776,780</link.rule.ids></links><search><creatorcontrib>Piotrowski, Tomasz</creatorcontrib><creatorcontrib>Ismayilov, Rafail</creatorcontrib><creatorcontrib>Frey, Matthias</creatorcontrib><creatorcontrib>Cavalcante, Renato L G</creatorcontrib><title>Inverse Feasibility in Over-the-Air Federated Learning</title><title>arXiv.org</title><description>We introduce the concept of inverse feasibility for linear forward models as a tool to enhance OTA FL algorithms. Inverse feasibility is defined as an upper bound on the condition number of the forward operator as a function of its parameters. We analyze an existing OTA FL model using this definition, identify areas for improvement, and propose a new OTA FL model. Numerical experiments illustrate the main implications of the theoretical results. The proposed framework, which is based on inverse problem theory, can potentially complement existing notions of security and privacy by providing additional desirable characteristics to networks.</description><subject>Federated learning</subject><subject>Iterative methods</subject><subject>Security</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>BENPR</sourceid><recordid>eNpjYuA0MjY21LUwMTLiYOAtLs4yMDAwMjM3MjU15mQw88wrSy0qTlVwS00szkzKzMksqVTIzFPwB4rqlmSk6jpmFgHlUlKLEktSUxR8UhOL8jLz0nkYWNMSc4pTeaE0N4Oym2uIs4duQVF-YWlqcUl8Vn5pUR5QKt7I3MTQ0NjA2NzImDhVAJUrNMY</recordid><startdate>20240219</startdate><enddate>20240219</enddate><creator>Piotrowski, Tomasz</creator><creator>Ismayilov, Rafail</creator><creator>Frey, Matthias</creator><creator>Cavalcante, Renato L G</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope></search><sort><creationdate>20240219</creationdate><title>Inverse Feasibility in Over-the-Air Federated Learning</title><author>Piotrowski, Tomasz ; Ismayilov, Rafail ; Frey, Matthias ; Cavalcante, Renato L G</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_27411303723</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Federated learning</topic><topic>Iterative methods</topic><topic>Security</topic><toplevel>online_resources</toplevel><creatorcontrib>Piotrowski, Tomasz</creatorcontrib><creatorcontrib>Ismayilov, Rafail</creatorcontrib><creatorcontrib>Frey, Matthias</creatorcontrib><creatorcontrib>Cavalcante, Renato L G</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science &amp; Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection (ProQuest)</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Piotrowski, Tomasz</au><au>Ismayilov, Rafail</au><au>Frey, Matthias</au><au>Cavalcante, Renato L G</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>Inverse Feasibility in Over-the-Air Federated Learning</atitle><jtitle>arXiv.org</jtitle><date>2024-02-19</date><risdate>2024</risdate><eissn>2331-8422</eissn><abstract>We introduce the concept of inverse feasibility for linear forward models as a tool to enhance OTA FL algorithms. Inverse feasibility is defined as an upper bound on the condition number of the forward operator as a function of its parameters. We analyze an existing OTA FL model using this definition, identify areas for improvement, and propose a new OTA FL model. Numerical experiments illustrate the main implications of the theoretical results. The proposed framework, which is based on inverse problem theory, can potentially complement existing notions of security and privacy by providing additional desirable characteristics to networks.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier EISSN: 2331-8422
ispartof arXiv.org, 2024-02
issn 2331-8422
language eng
recordid cdi_proquest_journals_2741130372
source Freely Accessible Journals
subjects Federated learning
Iterative methods
Security
title Inverse Feasibility in Over-the-Air Federated Learning
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-06T05%3A50%3A29IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=document&rft.atitle=Inverse%20Feasibility%20in%20Over-the-Air%20Federated%20Learning&rft.jtitle=arXiv.org&rft.au=Piotrowski,%20Tomasz&rft.date=2024-02-19&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2741130372%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2741130372&rft_id=info:pmid/&rfr_iscdi=true