{"id":"https://openalex.org/W4315472353","doi":"https://doi.org/10.1109/cdc51059.2022.9992939","title":"One-Pass Learning via Bridging Orthogonal Gradient Descent and Recursive Least-Squares","display_name":"One-Pass Learning via Bridging Orthogonal Gradient Descent and Recursive Least-Squares","publication_year":2022,"publication_date":"2022-12-06","ids":{"openalex":"https://openalex.org/W4315472353","doi":"https://doi.org/10.1109/cdc51059.2022.9992939"},"language":"en","primary_location":{"id":"doi:10.1109/cdc51059.2022.9992939","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc51059.2022.9992939","pdf_url":null,"source":{"id":"https://openalex.org/S4363607710","display_name":"2022 IEEE 61st Conference on Decision and Control (CDC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE 61st Conference on Decision and Control (CDC)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5065293026","display_name":"Young-Jae Min","orcid":"https://orcid.org/0000-0002-0334-5560"},"institutions":[{"id":"https://openalex.org/I4210143601","display_name":"Decision Systems (United States)","ror":"https://ror.org/0434dpa13","country_code":"US","type":"company","lineage":["https://openalex.org/I4210143601"]},{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Youngjae Min","raw_affiliation_strings":["Massachusetts Institute of Technology,Laboratory for Information and Decision Systems,Cambridge,MA,USA,02139"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology,Laboratory for Information and Decision Systems,Cambridge,MA,USA,02139","institution_ids":["https://openalex.org/I4210143601","https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079986554","display_name":"Kwangjun Ahn","orcid":"https://orcid.org/0000-0001-5516-5775"},"institutions":[{"id":"https://openalex.org/I4210143601","display_name":"Decision Systems (United States)","ror":"https://ror.org/0434dpa13","country_code":"US","type":"company","lineage":["https://openalex.org/I4210143601"]},{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kwangjun Ahn","raw_affiliation_strings":["Massachusetts Institute of Technology,Laboratory for Information and Decision Systems,Cambridge,MA,USA,02139"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology,Laboratory for Information and Decision Systems,Cambridge,MA,USA,02139","institution_ids":["https://openalex.org/I4210143601","https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005748450","display_name":"Navid Azizan","orcid":"https://orcid.org/0000-0002-4299-2963"},"institutions":[{"id":"https://openalex.org/I4210143601","display_name":"Decision Systems (United States)","ror":"https://ror.org/0434dpa13","country_code":"US","type":"company","lineage":["https://openalex.org/I4210143601"]},{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Navid Azizan","raw_affiliation_strings":["Massachusetts Institute of Technology,Laboratory for Information and Decision Systems,Cambridge,MA,USA,02139"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology,Laboratory for Information and Decision Systems,Cambridge,MA,USA,02139","institution_ids":["https://openalex.org/I4210143601","https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5065293026"],"corresponding_institution_ids":["https://openalex.org/I4210143601","https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":1.8529,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.92026462,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"4720","last_page":"4725"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9983000159263611,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7360555529594421},{"id":"https://openalex.org/keywords/stochastic-gradient-descent","display_name":"Stochastic gradient descent","score":0.6961487531661987},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.624751091003418},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5494292974472046},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5242317318916321},{"id":"https://openalex.org/keywords/data-stream","display_name":"Data stream","score":0.4535544514656067},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.41123533248901367}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7360555529594421},{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.6961487531661987},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.624751091003418},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5494292974472046},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5242317318916321},{"id":"https://openalex.org/C2778484313","wikidata":"https://www.wikidata.org/wiki/Q1172540","display_name":"Data stream","level":2,"score":0.4535544514656067},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.41123533248901367},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc51059.2022.9992939","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc51059.2022.9992939","pdf_url":null,"source":{"id":"https://openalex.org/S4363607710","display_name":"2022 IEEE 61st Conference on Decision and Control (CDC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE 61st Conference on Decision and Control (CDC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W2133140216","https://openalex.org/W2595233870","https://openalex.org/W2743151379","https://openalex.org/W2809090039","https://openalex.org/W2912322140","https://openalex.org/W2949804919","https://openalex.org/W2954929116","https://openalex.org/W2963518130","https://openalex.org/W2963739929","https://openalex.org/W3005981462","https://openalex.org/W3018252856","https://openalex.org/W3197493216","https://openalex.org/W3202101816","https://openalex.org/W4243330440","https://openalex.org/W4315472353","https://openalex.org/W4385248679","https://openalex.org/W6635271509","https://openalex.org/W6752125765","https://openalex.org/W6752495264","https://openalex.org/W6753918066","https://openalex.org/W6756091659","https://openalex.org/W6769244778","https://openalex.org/W6800669710","https://openalex.org/W6803224767"],"related_works":["https://openalex.org/W1998698147","https://openalex.org/W4206903459","https://openalex.org/W2754816816","https://openalex.org/W4366280654","https://openalex.org/W3160167280","https://openalex.org/W4231621013","https://openalex.org/W4362706668","https://openalex.org/W3008318776","https://openalex.org/W1977633006","https://openalex.org/W2041416246"],"abstract_inverted_index":{"While":[0],"deep":[1,215],"neural":[2],"networks":[3],"are":[4],"capable":[5],"of":[6,61,84,160,222],"achieving":[7],"state-of-the-art":[8],"performance":[9],"in":[10,43,51,64,110,133,195],"various":[11],"domains,":[12],"their":[13],"training":[14],"typically":[15],"requires":[16],"iterating":[17],"for":[18,95,175,209,214],"many":[19,44],"passes":[20],"over":[21],"the":[22,39,48,59,81,108,115,119,140,153,158,161,179,196,203,206,220,223,228],"dataset.":[23],"However,":[24],"due":[25],"to":[26,100,118,194,205,227],"computational":[27],"and":[28,31,36,136,145],"memory":[29,154],"constraints":[30],"potential":[32],"privacy":[33],"concerns,":[34],"storing":[35],"accessing":[37],"all":[38],"data":[40,49,73,163],"is":[41,68,186],"impractical":[42],"real-world":[45],"scenarios":[46],"where":[47],"arrives":[50],"a":[52,66,111],"stream.":[53],"In":[54],"this":[55],"paper,":[56],"we":[57,87,127,172,201],"investigate":[58],"problem":[60],"one-pass":[62,96],"learning,":[63,138],"which":[65,98],"model":[67],"trained":[69],"on":[70,76,121],"sequentially":[71],"arriving":[72],"without":[74],"retraining":[75],"previous":[77,122],"datapoints.":[78,123],"Motivated":[79],"by":[80,156,183],"increasing":[82],"use":[83],"overparameterized":[85,176,211],"models,":[86,178,212],"develop":[88],"Orthogonal":[89],"Recursive":[90],"Fitting":[91],"(ORFit),":[92],"an":[93,165],"algorithm":[94,144,151,185],"learning":[97],"seeks":[99],"perfectly":[101],"fit":[102],"every":[103],"new":[104],"datapoint":[105],"while":[106],"changing":[107],"parameters":[109],"direction":[112],"that":[113],"causes":[114],"least":[116],"change":[117],"predictions":[120],"By":[124],"doing":[125],"so,":[126],"bridge":[128],"two":[129],"seemingly":[130],"distinct":[131],"algorithms":[132],"adaptive":[134],"filtering":[135],"machine":[137],"namely":[139],"recursive":[141],"least-squares":[142],"(RLS)":[143],"orthogonal":[146],"gradient":[147,189],"descent":[148,190],"(OGD).":[149],"Our":[150,217],"uses":[152],"efficiently":[155],"exploiting":[157],"structure":[159],"streaming":[162],"via":[164],"incremental":[166],"principal":[167],"component":[168],"analysis":[169],"(IPCA).":[170],"Further,":[171],"show":[173,219],"that,":[174],"linear":[177],"parameter":[180],"vector":[181],"obtained":[182],"our":[184],"what":[187],"stochastic":[188],"(SGD)":[191],"would":[192],"converge":[193],"standard":[197],"multi-pass":[198],"setting.":[199],"Finally,":[200],"generalize":[202],"results":[204],"nonlinear":[207],"setting":[208],"highly":[210],"relevant":[213],"learning.":[216],"experiments":[218],"effectiveness":[221],"proposed":[224],"method":[225],"compared":[226],"baselines.":[229]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-04-15T08:11:43.952461","created_date":"2025-10-10T00:00:00"}