A Learning-Aided Flexible Gradient Descent Approach to MISO Beamforming

This letter proposes a learning aided gradient descent (LAGD) algorithm to solve the weighted sum rate (WSR) maximization problem for multiple-input single-output (MISO) beamforming. The proposed LAGD algorithm directly optimizes the transmit precoder through implicit gradient descent based iteratio...

Full description

Saved in:
Bibliographic Details
Published inIEEE wireless communications letters Vol. 11; no. 9; pp. 1895 - 1899
Main Authors Yang, Zhixiong, Xia, Jing-Yuan, Luo, Junshan, Zhang, Shuanghui, Gunduz, Deniz
Format Journal Article
LanguageEnglish
Published Piscataway IEEE 01.09.2022
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects
Online AccessGet full text
ISSN2162-2337
2162-2345
2162-2345
DOI10.1109/LWC.2022.3186160

Cover

Abstract This letter proposes a learning aided gradient descent (LAGD) algorithm to solve the weighted sum rate (WSR) maximization problem for multiple-input single-output (MISO) beamforming. The proposed LAGD algorithm directly optimizes the transmit precoder through implicit gradient descent based iterations, at each of which the optimization strategy is determined by a neural network, and thus, is dynamic and adaptive. At each instance of the problem, this network is initialized randomly, and updated throughout the iterative solution process. Therefore, the LAGD algorithm can be implemented at any signal-to-noise ratio (SNR) and for arbitrary antenna/user numbers, does not require labelled data or training prior to deployment. Numerical results show that the LAGD algorithm can outperform of the well-known WMMSE algorithm as well as other learning-based solutions with a modest computational complexity. Our code is available at https://github.com/XiaGroup/LAGD .
AbstractList This letter proposes a learning aided gradient descent (LAGD) algorithm to solve the weighted sum rate (WSR) maximization problem for multiple-input single-output (MISO) beamforming. The proposed LAGD algorithm directly optimizes the transmit precoder through implicit gradient descent based iterations, at each of which the optimization strategy is determined by a neural network, and thus, is dynamic and adaptive. At each instance of the problem, this network is initialized randomly, and updated throughout the iterative solution process. Therefore, the LAGD algorithm can be implemented at any signal-to-noise ratio (SNR) and for arbitrary antenna/user numbers, does not require labelled data or training prior to deployment. Numerical results show that the LAGD algorithm can outperform of the well-known WMMSE algorithm as well as other learning-based solutions with a modest computational complexity. Our code is available at https://github.com/XiaGroup/LAGD .
Author Yang, Zhixiong
Luo, Junshan
Gunduz, Deniz
Xia, Jing-Yuan
Zhang, Shuanghui
Author_xml – sequence: 1
  givenname: Zhixiong
  orcidid: 0000-0002-2667-3903
  surname: Yang
  fullname: Yang, Zhixiong
  email: yzx21@nudt.edu.cn
  organization: College of Electronic Engineering, National University of Defense Technology, Changsha, China
– sequence: 2
  givenname: Jing-Yuan
  orcidid: 0000-0003-4329-0354
  surname: Xia
  fullname: Xia, Jing-Yuan
  email: j.xia16@imperial.ac.uk
  organization: College of Electronic Engineering, National University of Defense Technology, Changsha, China
– sequence: 3
  givenname: Junshan
  surname: Luo
  fullname: Luo, Junshan
  email: luojunshan10@nudt.edu.cn
  organization: College of Electronic Engineering, National University of Defense Technology, Changsha, China
– sequence: 4
  givenname: Shuanghui
  orcidid: 0000-0002-7496-5433
  surname: Zhang
  fullname: Zhang, Shuanghui
  email: shzhang3@126.com
  organization: College of Electronic Engineering, National University of Defense Technology, Changsha, China
– sequence: 5
  givenname: Deniz
  orcidid: 0000-0002-7725-395X
  surname: Gunduz
  fullname: Gunduz, Deniz
  email: d.gunduz@imperial.ac.uk
  organization: Department of Electrical and Electronic Engineering, Imperial College London, London, U.K
BookMark eNptkL1PwzAUxC1UJErpjsQSiTnFH03ijKHQUimoAyBGy3GewVXqBCdV6X-Pq1QdKt5yb7jf6XTXaGBrCwjdEjwhBKcP-edsQjGlE0Z4TGJ8gYaUxDSkbBoNTj9LrtC4bdfYX4wJJXyIFlmQg3TW2K8wMyWUwbyCX1NUECycLA3YLniCVh00axpXS_UddHXwunxbBY8gN7p2Gw_foEstqxbGRx2hj_nz--wlzFeL5SzLQ8UY60IqI445xyRlKWgsZakV0xpkoVPtC8ZRATKeMlVwHjHOirSUqZoSXQCBBGs2QqTP3dpG7neyqkTjzEa6vSBYHMYQ1U6JwxjiOIZn7nvG1__ZQtuJdb111tcUNCEURzHjqXfFvUu5um0daKFMJztT285JU53i_dbn8fgMPG_0D3LXIwYATvaU4yhJGPsDD9SIjw
CODEN IWCLAF
CitedBy_id crossref_primary_10_1109_TPAMI_2024_3400041
crossref_primary_10_1007_s00034_024_02976_9
crossref_primary_10_1016_j_phycom_2024_102429
crossref_primary_10_1109_ACCESS_2024_3406527
crossref_primary_10_1109_LWC_2024_3436576
crossref_primary_10_1109_LWC_2023_3329036
crossref_primary_10_1109_TCSVT_2023_3318401
crossref_primary_10_1109_TWC_2023_3326091
crossref_primary_10_1109_TSP_2023_3238275
crossref_primary_10_1109_TWC_2022_3220784
Cites_doi 10.1109/COMST.2017.2750201
10.1109/TWC.2021.3071480
10.1109/ICASSP39728.2021.9414561
10.1109/ACCESS.2018.2887308
10.1109/JSAC.2019.2929380
10.1109/T-WC.2008.070851
10.1109/TCOMM.2019.2960361
10.1109/LGRS.2018.2866567
10.1109/VTCFall.2013.6692147
10.1109/LGRS.2022.3184311
10.1109/TCOMM.2004.840638
10.1109/TSP.2018.2866382
10.1109/TWC.2021.3111843
10.1109/JSEN.2020.3025053
10.1109/ACSSC.2009.5470055
10.1109/TSP.2011.2147784
10.1109/LWC.2020.3007198
10.1109/TNNLS.2022.3165627
10.1109/JSAC.2010.101206
10.1109/TSP.2020.3021257
10.1109/JSTSP.2007.914876
10.1109/ISIT45174.2021.9518251
ContentType Journal Article
Copyright Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2022
Copyright_xml – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2022
DBID 97E
RIA
RIE
AAYXX
CITATION
7SP
8FD
L7M
ADTOC
UNPAY
DOI 10.1109/LWC.2022.3186160
DatabaseName IEEE Xplore (IEEE)
IEEE All-Society Periodicals Package (ASPP) 1998–Present
IEEE Electronic Library (IEL)
CrossRef
Electronics & Communications Abstracts
Technology Research Database
Advanced Technologies Database with Aerospace
Unpaywall for CDI: Periodical Content
Unpaywall
DatabaseTitle CrossRef
Technology Research Database
Advanced Technologies Database with Aerospace
Electronics & Communications Abstracts
DatabaseTitleList
Technology Research Database
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://proxy.k.utb.cz/login?url=https://ieeexplore.ieee.org/
  sourceTypes: Publisher
– sequence: 2
  dbid: UNPAY
  name: Unpaywall
  url: https://proxy.k.utb.cz/login?url=https://unpaywall.org/
  sourceTypes: Open Access Repository
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISSN 2162-2345
EndPage 1899
ExternalDocumentID oai:iris.unimore.it:11380/1286025
10_1109_LWC_2022_3186160
9805773
Genre orig-research
GrantInformation_xml – fundername: European Research Council through Project BEACON
  grantid: 677854
  funderid: 10.13039/501100000781
– fundername: National Natural Science Foundation of China
  grantid: 62171448; 61921001; 62131020; 62022091
  funderid: 10.13039/501100001809
– fundername: CHIST-ERA
  grantid: CHISTERA-18-SDCDN-001; EPSRC-EP/T023600/1
  funderid: 10.13039/501100001942
– fundername: Natural Science Fund for Young Talents of Hunan Province (NSFYT) of Hunan
  grantid: 2020RC3029
  funderid: 10.13039/501100004735
GroupedDBID 0R~
4.4
5VS
6IK
97E
AAJGR
AARMG
AASAJ
AAWTH
ABAZT
ABQJQ
ABVLG
AGQYO
AGSQL
AHBIQ
AKJIK
AKQYR
ALMA_UNASSIGNED_HOLDINGS
ATWAV
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
EBS
EJD
IES
IFIPE
IPLJI
JAVBF
M43
OCL
RIA
RIE
RNS
AAYXX
CITATION
7SP
8FD
L7M
ADTOC
UNPAY
ID FETCH-LOGICAL-c333t-2a5808801939ef0aadfc3ffeabf9f33765bea643cb885383b9da9c41fbe1e70f3
IEDL.DBID RIE
ISSN 2162-2337
2162-2345
IngestDate Sun Oct 26 03:50:49 EDT 2025
Mon Jun 30 05:51:22 EDT 2025
Wed Oct 01 02:44:34 EDT 2025
Thu Apr 24 22:59:49 EDT 2025
Wed Aug 27 02:14:24 EDT 2025
IsDoiOpenAccess false
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 9
Language English
License https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html
https://doi.org/10.15223/policy-029
https://doi.org/10.15223/policy-037
cc-by
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c333t-2a5808801939ef0aadfc3ffeabf9f33765bea643cb885383b9da9c41fbe1e70f3
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ORCID 0000-0002-2667-3903
0000-0003-4329-0354
0000-0002-7496-5433
0000-0002-7725-395X
OpenAccessLink https://proxy.k.utb.cz/login?url=http://hdl.handle.net/11380/1286025
PQID 2712056389
PQPubID 2040496
PageCount 5
ParticipantIDs crossref_citationtrail_10_1109_LWC_2022_3186160
proquest_journals_2712056389
ieee_primary_9805773
crossref_primary_10_1109_LWC_2022_3186160
unpaywall_primary_10_1109_lwc_2022_3186160
ProviderPackageCode CITATION
AAYXX
PublicationCentury 2000
PublicationDate 2022-09-01
PublicationDateYYYYMMDD 2022-09-01
PublicationDate_xml – month: 09
  year: 2022
  text: 2022-09-01
  day: 01
PublicationDecade 2020
PublicationPlace Piscataway
PublicationPlace_xml – name: Piscataway
PublicationTitle IEEE wireless communications letters
PublicationTitleAbbrev LWC
PublicationYear 2022
Publisher IEEE
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml – name: IEEE
– name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References ref13
ref12
ref23
ref15
ref14
ref20
ref11
ref10
ref21
Kingma (ref22) 2014
ref2
ref1
ref17
ref16
ref19
ref18
ref8
ref7
ref9
ref4
ref3
ref6
ref5
References_xml – ident: ref2
  doi: 10.1109/COMST.2017.2750201
– ident: ref17
  doi: 10.1109/TWC.2021.3071480
– ident: ref16
  doi: 10.1109/ICASSP39728.2021.9414561
– ident: ref20
  doi: 10.1109/ACCESS.2018.2887308
– ident: ref9
  doi: 10.1109/JSAC.2019.2929380
– volume-title: arXiv:1412.6980
  year: 2014
  ident: ref22
  article-title: Adam: A method for stochastic optimization
– ident: ref6
  doi: 10.1109/T-WC.2008.070851
– ident: ref12
  doi: 10.1109/TCOMM.2019.2960361
– ident: ref18
  doi: 10.1109/LGRS.2018.2866567
– ident: ref5
  doi: 10.1109/VTCFall.2013.6692147
– ident: ref21
  doi: 10.1109/LGRS.2022.3184311
– ident: ref3
  doi: 10.1109/TCOMM.2004.840638
– ident: ref11
  doi: 10.1109/TSP.2018.2866382
– ident: ref15
  doi: 10.1109/TWC.2021.3111843
– ident: ref19
  doi: 10.1109/JSEN.2020.3025053
– ident: ref7
  doi: 10.1109/ACSSC.2009.5470055
– ident: ref8
  doi: 10.1109/TSP.2011.2147784
– ident: ref13
  doi: 10.1109/LWC.2020.3007198
– ident: ref23
  doi: 10.1109/TNNLS.2022.3165627
– ident: ref4
  doi: 10.1109/JSAC.2010.101206
– ident: ref10
  doi: 10.1109/TSP.2020.3021257
– ident: ref1
  doi: 10.1109/JSTSP.2007.914876
– ident: ref14
  doi: 10.1109/ISIT45174.2021.9518251
SSID ssj0000601218
Score 2.4228287
Snippet This letter proposes a learning aided gradient descent (LAGD) algorithm to solve the weighted sum rate (WSR) maximization problem for multiple-input...
SourceID unpaywall
proquest
crossref
ieee
SourceType Open Access Repository
Aggregation Database
Enrichment Source
Index Database
Publisher
StartPage 1895
SubjectTerms Algorithms
Array signal processing
Beamforming
Computational complexity
Heuristic algorithms
implicit gradient descent
Iterative methods
Iterative solution
Machine learning
Multi-user MISO downlink
Neural networks
Optimization
Signal processing
Signal to noise ratio
Training
unsupervised learning
SummonAdditionalLinks – databaseName: Unpaywall
  dbid: UNPAY
  link: http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlZ3LT9wwEIdHdDm0HPqiiKUU-dBLK4WN441jH1PoQqtCK7Wr0lPkJ0KEBUFWqP3rO06cLQ8JqbdEsuXIM_b8rIy_AXjrMKZJFAaJVYVPQolCXFLCJmzsjXXcGtViFw8O-f50_PkoP1qCvuDdHbwApUykI9xCOYbmR7DMcxTcA1ieHn4rf4WycZRnScZaMmZ8Huf9z8hUjurrQCnMMjyZCk5bDOW_4NNWU7klLB_PZxfq97Wq6xsxZvIMdvubOl1qyen2vNHb5s99cONDn_8cnkaNScrOKV7Akpu9hJUb5MFV2CtJJKseJ-WJdZZMAhlT147sXbZZYA3Z7UhPpIzYcdKck4NP37-SD06dBa2LnV_BdPLxx85-EmsqJIYx1iSZygVuLCjsmHQ-Vcp6w7x3SnvpcSJ5rp1ClWK0wEAumJZWSTOmXjvqitSzNRjMzmduHYjUXGqtuaMCjxlGCWUKq1KVo4q0lPkhjPrJrkwEjoe6F3XVHjxSWX35uVMF81TRPEN4t-hx0cE2Hmi7Guy3aCcFKs-CDWGzt2cVV-NVlRU0Q6GH2mwI7xc2vjcEesutITb-p_FreBJeu_SzTRg0l3P3BvVKo7eiv_4FkDfgng
  priority: 102
  providerName: Unpaywall
Title A Learning-Aided Flexible Gradient Descent Approach to MISO Beamforming
URI https://ieeexplore.ieee.org/document/9805773
https://www.proquest.com/docview/2712056389
http://hdl.handle.net/11380/1286025
UnpaywallVersion submittedVersion
Volume 11
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVIEE
  databaseName: IEEE Electronic Library (IEL)
  customDbUrl:
  eissn: 2162-2345
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0000601218
  issn: 2162-2345
  databaseCode: RIE
  dateStart: 20120101
  isFulltext: true
  titleUrlDefault: https://ieeexplore.ieee.org/
  providerName: IEEE
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV1Lb9QwEB615QAceJWKLaXygQuI7Cb2bmIfQ2FbEFuQYEU5RX6MESLsVm1WFfx6xk42tIAQtxzGmmTGznxjj78BeIwU0xQBg8TpwiehRSEtKekSMfbWYe6sjrSLs-P8aD5-fTI52YBn_V0YRIzFZzgMj_Es3y3tKmyVjZQkdFGITdgsZN7e1er3UwKvCI_beTzLecKFKNankqkavfl4QLkg55SiyjyLfJS_olBsq3IFYV5fLU719wtd15eCzfQ2zNav2daYfB2uGjO0P35jcPzf77gDtzrUycp2mtyFDVzcg5uXuAi34bBkHdfq56T84tCxaeDKNDWyw7NYF9awFy33Eys7InLWLNns1fu37DnqbwH90uD7MJ--_HBwlHRdFhIrhGgSrieSfjUE9YRCn2rtvBXeozZeebJiPjGoCbdYIym0S2GU08qOM28wwyL1Yge2FssFPgCmTK6MMTlmkhIPq6W2hdOpnhCudJnwAxitrV7ZjoI8dMKoq5iKpKoiP1XBT1XnpwE86UectvQb_5DdDqbu5TorD2Bv7diqW5_nFS8yTtCP0NoAnvbO_kNFfWGvqNj9u4qHcCNItaVne7DVnK3wEWGVxuzHSboP1-bH78pPPwHj0OTP
linkProvider IEEE
linkToHtml http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV1Lb9QwEB6VcigceJWKLQV84AIiu4mdl49LYbuF3XKgFb1FfowRIuxWbVYV_HrGTja0gBC3HDyaZMbOfGOPvwF4jhTTJAGDyKrCRb5FIS2p0kYidcZibo0KtIvzo3x6kr47zU434FV_FwYRQ_EZDv1jOMu3S7PyW2UjWRK6KMQNuJmlaZq1t7X6HRXPLMLDhh5Pch5xIYr1uWQsR7NP-5QNck5JapkngZHyVxwKjVWuYcyt1eJMfb9UdX0l3Ezuwnz9om2VydfhqtFD8-M3Dsf__ZJ7cKfDnWzcTpT7sIGLB3D7ChvhNhyMWce2-jkaf7Fo2cSzZeoa2cF5qAxr2JuW_YmNOypy1izZ_PDjB_Ya1TePf0n4IZxM3h7vT6Ouz0JkhBBNxFVW0s-GwJ6Q6GKlrDPCOVTaSUdWzDONipCL0SUF91JoaZU0aeI0JljETuzA5mK5wEfApM6l1jrHpKTUw6hSmcKqWGWELG0i3ABGa6tXpiMh970w6iokI7GsyE-V91PV-WkAL3qJs5aA4x9jt72p-3GdlQewt3Zs1a3Qi4oXCSfwR3htAC97Z_-hor4011Ts_l3FM9iaHs9n1ezw6P1juOUl2kK0Pdhszlf4hJBLo5-GCfsT0oXmbA
linkToUnpaywall http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlZ3LT9wwEIdHdDm0HPqiiKUU-dBLK4WN441jH1PoQqtCK7Wr0lPkJ0KEBUFWqP3rO06cLQ8JqbdEsuXIM_b8rIy_AXjrMKZJFAaJVYVPQolCXFLCJmzsjXXcGtViFw8O-f50_PkoP1qCvuDdHbwApUykI9xCOYbmR7DMcxTcA1ieHn4rf4WycZRnScZaMmZ8Huf9z8hUjurrQCnMMjyZCk5bDOW_4NNWU7klLB_PZxfq97Wq6xsxZvIMdvubOl1qyen2vNHb5s99cONDn_8cnkaNScrOKV7Akpu9hJUb5MFV2CtJJKseJ-WJdZZMAhlT147sXbZZYA3Z7UhPpIzYcdKck4NP37-SD06dBa2LnV_BdPLxx85-EmsqJIYx1iSZygVuLCjsmHQ-Vcp6w7x3SnvpcSJ5rp1ClWK0wEAumJZWSTOmXjvqitSzNRjMzmduHYjUXGqtuaMCjxlGCWUKq1KVo4q0lPkhjPrJrkwEjoe6F3XVHjxSWX35uVMF81TRPEN4t-hx0cE2Hmi7Guy3aCcFKs-CDWGzt2cVV-NVlRU0Q6GH2mwI7xc2vjcEesutITb-p_FreBJeu_SzTRg0l3P3BvVKo7eiv_4FkDfgng
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=A+Learning-Aided+Flexible+Gradient+Descent+Approach+to+MISO+Beamforming&rft.jtitle=IEEE+wireless+communications+letters&rft.au=Yang%2C+Zhixiong&rft.au=Xia%2C+Jing-Yuan&rft.au=Luo%2C+Junshan&rft.au=Zhang%2C+Shuanghui&rft.date=2022-09-01&rft.pub=IEEE&rft.issn=2162-2337&rft.volume=11&rft.issue=9&rft.spage=1895&rft.epage=1899&rft_id=info:doi/10.1109%2FLWC.2022.3186160&rft.externalDocID=9805773
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2162-2337&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2162-2337&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2162-2337&client=summon