Decentralized Descent Optimization With Stochastic Gradient Signs for Device-to-Device Networks
We propose an algorithm for decentralized optimization in wireless device-to-device (D2D) networks of pervasive devices such as sensors or 5G handsets, in which the signs of stochastic gradient are used for descent steps. Our algorithm has the convergence rate of {O} (1/( nT )) in which {n} is th...
Gespeichert in:
| Veröffentlicht in: | IEEE wireless communications letters 2021-09, Vol.10 (9), p.1939-1943 |
|---|---|
| Hauptverfasser: | , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 1943 |
|---|---|
| container_issue | 9 |
| container_start_page | 1939 |
| container_title | IEEE wireless communications letters |
| container_volume | 10 |
| creator | Phuong, Tran Thi Phong, Le Trieu |
| description | We propose an algorithm for decentralized optimization in wireless device-to-device (D2D) networks of pervasive devices such as sensors or 5G handsets, in which the signs of stochastic gradient are used for descent steps. Our algorithm has the convergence rate of {O} (1/( nT )) in which {n} is the number of devices and {T} is the number of learning iterations, saving the communication efficiency by at least 64 times when compared with previous results, and being relatively robust to unexpected errors of adversarial scaling in communication. Theoretical claims are verified by numerical results on a standard benchmark dataset. |
| doi_str_mv | 10.1109/LWC.2021.3087156 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_RIE</sourceid><recordid>TN_cdi_ieee_primary_9448084</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>9448084</ieee_id><sourcerecordid>2570191825</sourcerecordid><originalsourceid>FETCH-LOGICAL-c291t-6ebb73e6cb0881c485c579fceaac967935b4e9e2105f05dd6c97d0c49da775913</originalsourceid><addsrcrecordid>eNo9kNFLwzAQh4MoOObeBV8KPncmadMkj7LpFIZ7mLLHkKZXl7k1M8kU99fb0rF7uTv4fnfwIXRL8JgQLB_mq8mYYkrGGRacsOICDSgpaEqznF2e54xfo1EIG9xWgQklYoDUFAw00eutPUKVTCF0a7LYR7uzRx2ta5KVjetkGZ1Z6xCtSWZeV7ajlvazCUntfJv7sQbS6NJ-St4g_jr_FW7QVa23AUanPkQfz0_vk5d0vpi9Th7nqaGSxLSAsuQZFKbEQhCTC2YYl7UBrY0suMxYmYMESjCrMauqwkheYZPLSnPOJMmG6L6_u_fu-wAhqo07-KZ9qSjjmEgiKGsp3FPGuxA81Grv7U77P0Ww6kyq1qTqTKqTyTZy10csAJxxmecCizz7BwUPb2U</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2570191825</pqid></control><display><type>article</type><title>Decentralized Descent Optimization With Stochastic Gradient Signs for Device-to-Device Networks</title><source>IEEE Electronic Library (IEL)</source><creator>Phuong, Tran Thi ; Phong, Le Trieu</creator><creatorcontrib>Phuong, Tran Thi ; Phong, Le Trieu</creatorcontrib><description><![CDATA[We propose an algorithm for decentralized optimization in wireless device-to-device (D2D) networks of pervasive devices such as sensors or 5G handsets, in which the signs of stochastic gradient are used for descent steps. Our algorithm has the convergence rate of <inline-formula> <tex-math notation="LaTeX">{O} </tex-math></inline-formula>(1/( nT )) in which <inline-formula> <tex-math notation="LaTeX">{n} </tex-math></inline-formula> is the number of devices and <inline-formula> <tex-math notation="LaTeX">{T} </tex-math></inline-formula> is the number of learning iterations, saving the communication efficiency by at least 64 times when compared with previous results, and being relatively robust to unexpected errors of adversarial scaling in communication. Theoretical claims are verified by numerical results on a standard benchmark dataset.]]></description><identifier>ISSN: 2162-2337</identifier><identifier>EISSN: 2162-2345</identifier><identifier>DOI: 10.1109/LWC.2021.3087156</identifier><identifier>CODEN: IWCLAF</identifier><language>eng</language><publisher>Piscataway: IEEE</publisher><subject>Algorithms ; Benchmark testing ; communication efficiency ; Convergence ; D2D networks ; gradient descent ; Optimization ; Robustness ; Robustness (mathematics) ; Wireless communication ; Wireless networks ; Wireless sensor networks</subject><ispartof>IEEE wireless communications letters, 2021-09, Vol.10 (9), p.1939-1943</ispartof><rights>Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2021</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c291t-6ebb73e6cb0881c485c579fceaac967935b4e9e2105f05dd6c97d0c49da775913</citedby><cites>FETCH-LOGICAL-c291t-6ebb73e6cb0881c485c579fceaac967935b4e9e2105f05dd6c97d0c49da775913</cites><orcidid>0000-0002-0383-8891 ; 0000-0003-2219-1867</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/9448084$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>314,776,780,792,27901,27902,54733</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/9448084$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Phuong, Tran Thi</creatorcontrib><creatorcontrib>Phong, Le Trieu</creatorcontrib><title>Decentralized Descent Optimization With Stochastic Gradient Signs for Device-to-Device Networks</title><title>IEEE wireless communications letters</title><addtitle>LWC</addtitle><description><![CDATA[We propose an algorithm for decentralized optimization in wireless device-to-device (D2D) networks of pervasive devices such as sensors or 5G handsets, in which the signs of stochastic gradient are used for descent steps. Our algorithm has the convergence rate of <inline-formula> <tex-math notation="LaTeX">{O} </tex-math></inline-formula>(1/( nT )) in which <inline-formula> <tex-math notation="LaTeX">{n} </tex-math></inline-formula> is the number of devices and <inline-formula> <tex-math notation="LaTeX">{T} </tex-math></inline-formula> is the number of learning iterations, saving the communication efficiency by at least 64 times when compared with previous results, and being relatively robust to unexpected errors of adversarial scaling in communication. Theoretical claims are verified by numerical results on a standard benchmark dataset.]]></description><subject>Algorithms</subject><subject>Benchmark testing</subject><subject>communication efficiency</subject><subject>Convergence</subject><subject>D2D networks</subject><subject>gradient descent</subject><subject>Optimization</subject><subject>Robustness</subject><subject>Robustness (mathematics)</subject><subject>Wireless communication</subject><subject>Wireless networks</subject><subject>Wireless sensor networks</subject><issn>2162-2337</issn><issn>2162-2345</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><sourceid>RIE</sourceid><recordid>eNo9kNFLwzAQh4MoOObeBV8KPncmadMkj7LpFIZ7mLLHkKZXl7k1M8kU99fb0rF7uTv4fnfwIXRL8JgQLB_mq8mYYkrGGRacsOICDSgpaEqznF2e54xfo1EIG9xWgQklYoDUFAw00eutPUKVTCF0a7LYR7uzRx2ta5KVjetkGZ1Z6xCtSWZeV7ajlvazCUntfJv7sQbS6NJ-St4g_jr_FW7QVa23AUanPkQfz0_vk5d0vpi9Th7nqaGSxLSAsuQZFKbEQhCTC2YYl7UBrY0suMxYmYMESjCrMauqwkheYZPLSnPOJMmG6L6_u_fu-wAhqo07-KZ9qSjjmEgiKGsp3FPGuxA81Grv7U77P0Ww6kyq1qTqTKqTyTZy10csAJxxmecCizz7BwUPb2U</recordid><startdate>20210901</startdate><enddate>20210901</enddate><creator>Phuong, Tran Thi</creator><creator>Phong, Le Trieu</creator><general>IEEE</general><general>The Institute of Electrical and Electronics Engineers, Inc. (IEEE)</general><scope>97E</scope><scope>RIA</scope><scope>RIE</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7SP</scope><scope>8FD</scope><scope>L7M</scope><orcidid>https://orcid.org/0000-0002-0383-8891</orcidid><orcidid>https://orcid.org/0000-0003-2219-1867</orcidid></search><sort><creationdate>20210901</creationdate><title>Decentralized Descent Optimization With Stochastic Gradient Signs for Device-to-Device Networks</title><author>Phuong, Tran Thi ; Phong, Le Trieu</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c291t-6ebb73e6cb0881c485c579fceaac967935b4e9e2105f05dd6c97d0c49da775913</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>Algorithms</topic><topic>Benchmark testing</topic><topic>communication efficiency</topic><topic>Convergence</topic><topic>D2D networks</topic><topic>gradient descent</topic><topic>Optimization</topic><topic>Robustness</topic><topic>Robustness (mathematics)</topic><topic>Wireless communication</topic><topic>Wireless networks</topic><topic>Wireless sensor networks</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Phuong, Tran Thi</creatorcontrib><creatorcontrib>Phong, Le Trieu</creatorcontrib><collection>IEEE All-Society Periodicals Package (ASPP) 2005-present</collection><collection>IEEE All-Society Periodicals Package (ASPP) 1998-Present</collection><collection>IEEE Electronic Library (IEL)</collection><collection>CrossRef</collection><collection>Electronics & Communications Abstracts</collection><collection>Technology Research Database</collection><collection>Advanced Technologies Database with Aerospace</collection><jtitle>IEEE wireless communications letters</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Phuong, Tran Thi</au><au>Phong, Le Trieu</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Decentralized Descent Optimization With Stochastic Gradient Signs for Device-to-Device Networks</atitle><jtitle>IEEE wireless communications letters</jtitle><stitle>LWC</stitle><date>2021-09-01</date><risdate>2021</risdate><volume>10</volume><issue>9</issue><spage>1939</spage><epage>1943</epage><pages>1939-1943</pages><issn>2162-2337</issn><eissn>2162-2345</eissn><coden>IWCLAF</coden><abstract><![CDATA[We propose an algorithm for decentralized optimization in wireless device-to-device (D2D) networks of pervasive devices such as sensors or 5G handsets, in which the signs of stochastic gradient are used for descent steps. Our algorithm has the convergence rate of <inline-formula> <tex-math notation="LaTeX">{O} </tex-math></inline-formula>(1/( nT )) in which <inline-formula> <tex-math notation="LaTeX">{n} </tex-math></inline-formula> is the number of devices and <inline-formula> <tex-math notation="LaTeX">{T} </tex-math></inline-formula> is the number of learning iterations, saving the communication efficiency by at least 64 times when compared with previous results, and being relatively robust to unexpected errors of adversarial scaling in communication. Theoretical claims are verified by numerical results on a standard benchmark dataset.]]></abstract><cop>Piscataway</cop><pub>IEEE</pub><doi>10.1109/LWC.2021.3087156</doi><tpages>5</tpages><orcidid>https://orcid.org/0000-0002-0383-8891</orcidid><orcidid>https://orcid.org/0000-0003-2219-1867</orcidid></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISSN: 2162-2337 |
| ispartof | IEEE wireless communications letters, 2021-09, Vol.10 (9), p.1939-1943 |
| issn | 2162-2337 2162-2345 |
| language | eng |
| recordid | cdi_ieee_primary_9448084 |
| source | IEEE Electronic Library (IEL) |
| subjects | Algorithms Benchmark testing communication efficiency Convergence D2D networks gradient descent Optimization Robustness Robustness (mathematics) Wireless communication Wireless networks Wireless sensor networks |
| title | Decentralized Descent Optimization With Stochastic Gradient Signs for Device-to-Device Networks |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-28T13%3A19%3A00IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_RIE&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Decentralized%20Descent%20Optimization%20With%20Stochastic%20Gradient%20Signs%20for%20Device-to-Device%20Networks&rft.jtitle=IEEE%20wireless%20communications%20letters&rft.au=Phuong,%20Tran%20Thi&rft.date=2021-09-01&rft.volume=10&rft.issue=9&rft.spage=1939&rft.epage=1943&rft.pages=1939-1943&rft.issn=2162-2337&rft.eissn=2162-2345&rft.coden=IWCLAF&rft_id=info:doi/10.1109/LWC.2021.3087156&rft_dat=%3Cproquest_RIE%3E2570191825%3C/proquest_RIE%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2570191825&rft_id=info:pmid/&rft_ieee_id=9448084&rfr_iscdi=true |