{"id":"https://openalex.org/W6996943418","doi":null,"title":"Two New Applications of Tensors to Machine Learning for Wireless Communications","display_name":"Two New Applications of Tensors to Machine Learning for Wireless Communications","alternate_titles":[],"publication_year":2021,"publication_date":"2021-09-09","ids":{"openalex":"https://openalex.org/W6996943418"},"language":"en","primary_location":{"id":"pmh:oai:vtechworks.lib.vt.edu:10919/104970","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/10919/104970","pdf_url":"https://vtechworks.lib.vt.edu/bitstreams/558305b1-3515-47ca-ab1c-90340e48c59d/download","source":{"id":"https://openalex.org/S4306400248","display_name":"VTechWorks (Virginia Tech)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I859038795","host_organization_name":"Virginia Tech","host_organization_lineage":["https://openalex.org/I859038795"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Thesis"},"parent_works":[],"lineage":["https://openalex.org/W6996943418"],"child_works_count":0,"type":"dissertation","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://vtechworks.lib.vt.edu/bitstreams/558305b1-3515-47ca-ab1c-90340e48c59d/download","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5023686748","display_name":"Keerthana Bhogi","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":true,"contributor_roles":[],"raw_author_name":"Bhogi, Keerthana","raw_affiliation_strings":["Faculty of the Virginia Polytechnic Institute and State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of the Virginia Polytechnic Institute and State University","institution_ids":["https://openalex.org/I859038795"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5023686748"],"corresponding_institution_ids":["https://openalex.org/I859038795"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_pulled":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T12303","display_name":"Tensor decomposition and applications","score":0.7997999787330627,"subfield":{"id":"https://openalex.org/subfields/2605","display_name":"Computational Mathematics"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12303","display_name":"Tensor decomposition and applications","score":0.7997999787330627,"subfield":{"id":"https://openalex.org/subfields/2605","display_name":"Computational Mathematics"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10148","display_name":"Advanced MIMO Systems Optimization","score":0.05869999900460243,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10936","display_name":"Millimeter-Wave Propagation and Modeling","score":0.03200000151991844,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/tensors","display_name":"tensors","score":0.6869999766349792},{"id":"https://openalex.org/keywords/tensor-decomposition","display_name":"tensor decomposition","score":0.6439999938011169},{"id":"https://openalex.org/keywords/kronecker-product","display_name":"Kronecker product","score":0.8289999961853027},{"id":"https://openalex.org/keywords/full-dimension-mimo","display_name":"full-dimension MIMO","score":0.953000009059906},{"id":"https://openalex.org/keywords/uniform-planar-array","display_name":"uniform planar array","score":0.9079999923706055},{"id":"https://openalex.org/keywords/k-means-clustering","display_name":"K-means clustering","score":0.6669999957084656},{"id":"https://openalex.org/keywords/gradient-compression","display_name":"gradient compression","score":0.6240000128746033},{"id":"https://openalex.org/keywords/federated-learning","display_name":"federated learning","score":0.9490000009536743},{"id":"https://openalex.org/keywords/convolutional-neural-networks","display_name":"convolutional neural networks","score":0.9129999876022339},{"id":"https://openalex.org/keywords/compressed-sensing","display_name":"compressed sensing","score":0.8209999799728394},{"id":"https://openalex.org/keywords/gradient-reconstruction","display_name":"gradient reconstruction","score":0.4429999887943268},{"id":"https://openalex.org/keywords/spectral-efficiency","display_name":"spectral efficiency","score":0.4959999918937683},{"id":"https://openalex.org/keywords/wireless-communication","display_name":"wireless communication","score":0.4449999928474426},{"id":"https://openalex.org/keywords/data-driven-machine-learning","display_name":"data-driven machine learning","score":0.7039999961853027},{"id":"https://openalex.org/keywords/low-complexity-algorithms","display_name":"low-complexity algorithms","score":0.6029999852180481},{"id":"https://openalex.org/keywords/unsupervised-clustering","display_name":"unsupervised clustering","score":0.6620000004768372},{"id":"https://openalex.org/keywords/sparse-gradients","display_name":"sparse gradients","score":0.5}],"concepts":[{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3095000088214874},{"id":"https://openalex.org/C64543145","wikidata":"https://www.wikidata.org/wiki/Q162942","display_name":"Intersection (aeronautics)","level":2,"score":0.27889999747276306},{"id":"https://openalex.org/C2781032047","wikidata":"https://www.wikidata.org/wiki/Q938793","display_name":"Articular cartilage damage","level":5,"score":0.2676999866962433},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.25450000166893005},{"id":"https://openalex.org/C17212007","wikidata":"https://www.wikidata.org/wiki/Q5511111","display_name":"Fuzzy clustering","level":3,"score":0.23980000615119934},{"id":"https://openalex.org/C90673727","wikidata":"https://www.wikidata.org/wiki/Q901718","display_name":"Product (mathematics)","level":2,"score":0.23980000615119934},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.23739999532699585},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.23579999804496765},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23389999568462372},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.22529999911785126}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:vtechworks.lib.vt.edu:10919/104970","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/10919/104970","pdf_url":"https://vtechworks.lib.vt.edu/bitstreams/558305b1-3515-47ca-ab1c-90340e48c59d/download","source":{"id":"https://openalex.org/S4306400248","display_name":"VTechWorks (Virginia Tech)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I859038795","host_organization_name":"Virginia Tech","host_organization_lineage":["https://openalex.org/I859038795"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Thesis"}],"best_oa_location":{"id":"pmh:oai:vtechworks.lib.vt.edu:10919/104970","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/10919/104970","pdf_url":"https://vtechworks.lib.vt.edu/bitstreams/558305b1-3515-47ca-ab1c-90340e48c59d/download","source":{"id":"https://openalex.org/S4306400248","display_name":"VTechWorks (Virginia Tech)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I859038795","host_organization_name":"Virginia Tech","host_organization_lineage":["https://openalex.org/I859038795"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Thesis"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W6996943418.pdf","grobid_xml":"https://content.openalex.org/works/W6996943418.grobid-xml"},"referenced_works_count":95,"referenced_works":["https://openalex.org/W92008980","https://openalex.org/W1680189815","https://openalex.org/W1758773383","https://openalex.org/W1800261609","https://openalex.org/W1963826206","https://openalex.org/W1970176196","https://openalex.org/W1983467829","https://openalex.org/W1985290376","https://openalex.org/W1989885165","https://openalex.org/W1993482030","https://openalex.org/W1997783781","https://openalex.org/W2004026774","https://openalex.org/W2006021297","https://openalex.org/W2013912476","https://openalex.org/W2024165284","https://openalex.org/W2025603201","https://openalex.org/W2026933032","https://openalex.org/W2031107356","https://openalex.org/W2035399158","https://openalex.org/W2045512849","https://openalex.org/W2048050794","https://openalex.org/W2051528376","https://openalex.org/W2073469810","https://openalex.org/W2074863717","https://openalex.org/W2099238939","https://openalex.org/W2101641981","https://openalex.org/W2103537693","https://openalex.org/W2108747643","https://openalex.org/W2113271807","https://openalex.org/W2115152632","https://openalex.org/W2115543075","https://openalex.org/W2119412403","https://openalex.org/W2122111042","https://openalex.org/W2124583124","https://openalex.org/W2130667916","https://openalex.org/W2134383396","https://openalex.org/W2135279794","https://openalex.org/W2136559714","https://openalex.org/W2140099565","https://openalex.org/W2141200867","https://openalex.org/W2154102565","https://openalex.org/W2155639125","https://openalex.org/W2157009680","https://openalex.org/W2161515500","https://openalex.org/W2165266777","https://openalex.org/W2166670884","https://openalex.org/W2230684453","https://openalex.org/W2258054274","https://openalex.org/W2283463896","https://openalex.org/W2290739911","https://openalex.org/W2468422810","https://openalex.org/W2469230926","https://openalex.org/W2493309683","https://openalex.org/W2535838896","https://openalex.org/W2541884796","https://openalex.org/W2604974991","https://openalex.org/W2606891064","https://openalex.org/W2617766261","https://openalex.org/W2734256217","https://openalex.org/W2734408173","https://openalex.org/W2736068844","https://openalex.org/W2786602455","https://openalex.org/W2791651909","https://openalex.org/W2798329663","https://openalex.org/W2805997383","https://openalex.org/W2883059862","https://openalex.org/W2886124254","https://openalex.org/W2890924858","https://openalex.org/W2891970177","https://openalex.org/W2899051391","https://openalex.org/W2904648777","https://openalex.org/W2907379776","https://openalex.org/W2920095265","https://openalex.org/W2933910221","https://openalex.org/W2944099577","https://openalex.org/W2947333088","https://openalex.org/W2963145597","https://openalex.org/W2963647784","https://openalex.org/W2968166840","https://openalex.org/W2968239693","https://openalex.org/W2971330699","https://openalex.org/W2975296300","https://openalex.org/W2992306119","https://openalex.org/W2999074226","https://openalex.org/W3003523846","https://openalex.org/W3003689553","https://openalex.org/W3004277316","https://openalex.org/W3010264834","https://openalex.org/W3012121045","https://openalex.org/W3025636570","https://openalex.org/W3045898871","https://openalex.org/W3046653923","https://openalex.org/W3090615085","https://openalex.org/W3127479988","https://openalex.org/W3208185780"],"related_works":["https://openalex.org/W3177097878","https://openalex.org/W6885083924","https://openalex.org/W3087223394","https://openalex.org/W3189608635","https://openalex.org/W2910156841","https://openalex.org/W3003523846","https://openalex.org/W3092560887","https://openalex.org/W2736635927","https://openalex.org/W2126037235","https://openalex.org/W3130401643"],"abstract_inverted_index":{"With":[0],"the":[1,8,25,31,44,50,55,98,102,140,155,185,191,195,212,237,242,256,263,268,274,279,288,331,334,338,348,352,356,371,374,379,385,389,404,410,420,425,440,445,468,481,484,490,496,499],"increasing":[2],"number":[3],"of":[4,11,54,90,101,113,175,178,190,262,273,281,296,367,409,427,498],"wireless":[5,26,95],"devices":[6],"and":[7,52,187,270,354,365,373,401],"phenomenal":[9],"amount":[10],"data":[12,47,71,80,104,335],"that":[13,218,322,443,475,489],"is":[14,20,105,116,146,158,172,224,299,317],"being":[15],"generated":[16,336],"by":[17,76,337,342,345,419],"them,":[18],"there":[19],"a":[21,61,65,117,126,133,149,153,162,173,204,230,252,300,318,343,414,428,436,461],"growing":[22],"interest":[23],"in":[24,72,79,107,202,454],"communications":[27,96],"community":[28],"to":[29,48,68,92,166,184,251,267,287,324,391,403,423],"complement":[30],"traditional":[32],"model-driven":[33],"design":[34,123,196,222],"approaches":[35],"with":[36,132,310,351,431,450],"data-driven":[37],"machine":[38],"learning":[39,291,308],"(ML)-based":[40],"solutions.":[41],"However,":[42],"managing":[43],"large-scale":[45],"multi-dimensional":[46,70],"maintain":[49],"efficiency":[51],"scalability":[53],"ML":[56,93,320,328],"algorithms":[57],"has":[58],"obviously":[59],"been":[60],"challenge.":[62],"Tensors":[63],"provide":[64],"useful":[66],"framework":[67,474],"represent":[69],"an":[73,168,225,327,455],"integrated":[74],"manner":[75],"preserving":[77],"relationships":[78],"across":[81],"different":[82],"dimensions.":[83],"This":[84],"thesis":[85,115,298],"studies":[86],"two":[87,179],"new":[88],"applications":[89],"tensors":[91],"for":[94,125,206,306,406,439],"where":[97,236],"tensor":[99,118,163,416],"structure":[100,417],"concerned":[103],"exploited":[106],"novel":[108,437,462],"ways.":[109],"The":[110,293],"first":[111],"contribution":[112,295],"this":[114,219,248,297,477],"learning-based":[119],"low-complexity":[120],"precoder":[121,170,209,282],"codebook":[122,221,283,290],"technique":[124,165,305,400],"full-dimension":[127],"multiple-input":[128],"multiple-output":[129],"(FD-MIMO)":[130],"system":[131],"uniform":[134],"planar":[135],"antenna":[136],"(UPA)":[137],"array":[138],"at":[139,330,370,388],"transmitter":[141],"(Tx)":[142],"whose":[143],"channel":[144,157],"distribution":[145],"available":[147],"through":[148],"dataset.":[150],"Represented":[151],"as":[152],"tensor,":[154],"FD-MIMO":[156,192],"further":[159,246,459],"decomposed":[160],"using":[161,211,333,396],"decomposition":[164],"obtain":[167,392],"optimal":[169,207,238],"which":[171,265],"function":[174],"Kronecker-Product":[176],"(KP)":[177],"low-dimensional":[180,214,257,394],"precoders,":[181],"each":[182],"corresponding":[183],"horizontal":[186,269],"vertical":[188,271],"dimensions":[189,272],"channel.":[193],"From":[194],"perspective,":[197],"we":[198,360,383,487],"have":[199],"made":[200],"contributions":[201],"deriving":[203],"criterion":[205],"product":[208,220],"codebooks":[210],"obtained":[213],"precoders.":[215],"We":[216,245,412,434,458],"show":[217],"problem":[223,228,250],"unsupervised":[226],"clustering":[227,249],"on":[229,255,362,467],"Cartesian":[231],"Product":[232],"Grassmann":[233,259],"Manifold":[234],"(CPM),":[235],"cluster":[239],"centroids":[240],"form":[241],"desired":[243],"codebook.":[244],"simplify":[247],"$K$-means":[253],"algorithm":[254,465],"factor":[258],"manifolds":[260],"(GMs)":[261],"CPM":[264],"correspond":[266],"UPA,":[275],"thus":[276],"significantly":[277],"reducing":[278],"complexity":[280],"construction":[284],"when":[285],"compared":[286],"existing":[289],"techniques.":[292],"second":[294],"tensor-based":[301],"bandwidth-efficient":[302],"gradient":[303,380,429,492],"communication":[304,381],"federated":[307],"(FL)":[309],"convolutional":[311,368,421,441],"neural":[312],"networks":[313],"(CNNs).":[314],"Concisely,":[315],"FL":[316],"decentralized":[319],"approach":[321],"allows":[323],"jointly":[325],"train":[326],"model":[329],"server":[332,353,405],"distributed":[339],"users":[340,372,390],"coordinated":[341],"server,":[344,375],"sharing":[346],"only":[347],"local":[349],"gradients":[350,369,387,422,442],"not":[355],"raw":[357],"data.":[358],"Here,":[359],"focus":[361],"efficient":[363],"compression":[364],"reconstruction":[366,464,493],"respectively.":[376],"To":[377],"reduce":[378],"overhead,":[382],"compress":[384],"sparse":[386,452],"their":[393],"estimates":[395],"compressive":[397],"sensing":[398],"(CS)-based":[399],"transmit":[402],"joint":[407],"training":[408],"CNN.":[411],"exploit":[413],"natural":[415],"offered":[418],"demonstrate":[424,488],"correlation":[426],"element":[430],"its":[432,451],"neighbors.":[433],"propose":[435,460],"prior":[438,478],"captures":[444],"described":[446],"spatial":[447],"consistency":[448],"along":[449],"nature":[453],"appropriate":[456],"way.":[457],"Bayesian":[463],"based":[466],"Generalized":[469],"Approximate":[470],"Message":[471],"Passing":[472],"(GAMP)":[473],"exploits":[476],"information":[479],"about":[480],"gradients.":[482],"Through":[483],"numerical":[485],"simulations,":[486],"developed":[491],"method":[494],"improves":[495],"convergence":[497],"CNN":[500],"model.":[501]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W6996943418","counts_by_year":[],"updated_date":"2026-11-20T13:11:24.684918","created_date":"2025-10-10T00:00:00"}
