{"id":"https://openalex.org/W2914810015","doi":"https://doi.org/10.1109/bigdata.2018.8622392","title":"Streaming Algorithm for Big Data Logistic Regression","display_name":"Streaming Algorithm for Big Data Logistic Regression","publication_year":2018,"publication_date":"2018-12-01","ids":{"openalex":"https://openalex.org/W2914810015","doi":"https://doi.org/10.1109/bigdata.2018.8622392","mag":"2914810015"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata.2018.8622392","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2018.8622392","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5089355143","display_name":"Baijian Yang","orcid":"https://orcid.org/0000-0003-4440-3701"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Baijian Yang","raw_affiliation_strings":["Department of Computer and Information Technology, Purdue University, West Lafayette, IN, U.S.A","Department of Computer and Information Technology, Purdue University, West Lafayette, IN, 47907, U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer and Information Technology, Purdue University, West Lafayette, IN, U.S.A","institution_ids":["https://openalex.org/I219193219"]},{"raw_affiliation_string":"Department of Computer and Information Technology, Purdue University, West Lafayette, IN, 47907, U.S.A","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100761956","display_name":"Mengyao Wang","orcid":"https://orcid.org/0009-0003-3810-8164"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mengyao Wang","raw_affiliation_strings":["Department of Computer and Information Technology, Purdue University, West Lafayette, IN, U.S.A","Department of Computer and Information Technology, Purdue University, West Lafayette, IN, 47907, U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer and Information Technology, Purdue University, West Lafayette, IN, U.S.A","institution_ids":["https://openalex.org/I219193219"]},{"raw_affiliation_string":"Department of Computer and Information Technology, Purdue University, West Lafayette, IN, 47907, U.S.A","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084081479","display_name":"Zhenzhi Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhenzhi Xu","raw_affiliation_strings":["Department of Computer and Information Technology, Purdue University, West Lafayette, IN, U.S.A","Department of Computer and Information Technology, Purdue University, West Lafayette, IN, 47907, U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer and Information Technology, Purdue University, West Lafayette, IN, U.S.A","institution_ids":["https://openalex.org/I219193219"]},{"raw_affiliation_string":"Department of Computer and Information Technology, Purdue University, West Lafayette, IN, 47907, U.S.A","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089567067","display_name":"Tonglin Zhang","orcid":"https://orcid.org/0000-0003-3312-2293"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tonglin Zhang","raw_affiliation_strings":["Department of Statistics, Purdue University, West Lafayette, IN, U.S.A","Department of Statistics; Purdue University; West Lafayette; IN 47907; U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Statistics, Purdue University, West Lafayette, IN, U.S.A","institution_ids":["https://openalex.org/I219193219"]},{"raw_affiliation_string":"Department of Statistics; Purdue University; West Lafayette; IN 47907; U.S.A","institution_ids":["https://openalex.org/I219193219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I219193219"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"10","issue":null,"first_page":"2940","last_page":"2950"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10057","display_name":"Face and Expression Recognition","score":0.9182000160217285,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10057","display_name":"Face and Expression Recognition","score":0.9182000160217285,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/logistic-regression","display_name":"Logistic regression","score":0.7012701034545898},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7004695534706116},{"id":"https://openalex.org/keywords/logistic-model-tree","display_name":"Logistic model tree","score":0.46394965052604675},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.44652464985847473},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4102894067764282},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33432263135910034},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.308053195476532},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.28744229674339294}],"concepts":[{"id":"https://openalex.org/C151956035","wikidata":"https://www.wikidata.org/wiki/Q1132755","display_name":"Logistic regression","level":2,"score":0.7012701034545898},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7004695534706116},{"id":"https://openalex.org/C61722155","wikidata":"https://www.wikidata.org/wiki/Q6667643","display_name":"Logistic model tree","level":3,"score":0.46394965052604675},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.44652464985847473},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4102894067764282},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33432263135910034},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.308053195476532},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28744229674339294}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata.2018.8622392","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2018.8622392","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Big Data (Big Data)","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":13,"referenced_works":["https://openalex.org/W1525878169","https://openalex.org/W1981976602","https://openalex.org/W2004147962","https://openalex.org/W2015536388","https://openalex.org/W2109722477","https://openalex.org/W2117699623","https://openalex.org/W2121394390","https://openalex.org/W2173213060","https://openalex.org/W2189465200","https://openalex.org/W2520570087","https://openalex.org/W2784303361","https://openalex.org/W6676367512","https://openalex.org/W6687322159"],"related_works":["https://openalex.org/W2059099031","https://openalex.org/W4367335967","https://openalex.org/W4225160365","https://openalex.org/W2991210157","https://openalex.org/W1596769710","https://openalex.org/W1574918455","https://openalex.org/W4238660912","https://openalex.org/W2908249560","https://openalex.org/W2444264653","https://openalex.org/W2073229519"],"abstract_inverted_index":{"This":[0],"research":[1],"proposed":[2,77,106,136],"a":[3,109,140],"novel":[4],"fitting":[5],"algorithm":[6,19,43,107],"for":[7,52],"big":[8],"data":[9],"logistic":[10,124],"regression":[11,125],"by":[12],"combining":[13],"Fisher":[14],"Scoring":[15],"and":[16,25,47,63,114],"IRWLS.":[17],"The":[18,42,72],"enables":[20],"streamed":[21],"operation":[22],"to":[23,35,65,128],"fit":[24],"update":[26],"the":[27,33,37,76,105,117,129,135],"model":[28],"at":[29],"per-row":[30],"level,":[31],"without":[32],"need":[34],"store":[36],"entire":[38],"dataset":[39],"in":[40,94,98,133,143],"RAM.":[41],"is":[44],"fully":[45],"parallelizable":[46],"was":[48],"implemented":[49],"on":[50,61],"Spark":[51,62],"this":[53],"study.":[54],"A":[55],"set":[56],"of":[57,100],"experiments":[58],"were":[59],"conducted":[60],"Scikit-Learn":[64],"compare":[66],"its":[67],"performance":[68],"against":[69],"existing":[70],"approaches.":[71,126],"results":[73],"showed":[74],"that":[75,121],"method":[78],"can":[79],"provide":[80],"exact":[81],"results,":[82,86],"rather":[83],"than":[84],"approximate":[85],"with":[87],"significantly":[88],"fewer":[89],"iterations.":[90],"It":[91],"also":[92,138],"converged":[93],"merely":[95],"2":[96],"iterations":[97],"terms":[99],"prediction":[101],"accuracy.":[102,144],"More":[103],"importantly,":[104],"has":[108],"very":[110],"small":[111],"memory":[112,118],"footprint":[113],"completely":[115],"broke":[116],"barrier":[119],"problem":[120],"debilitated":[122],"conventional":[123],"Compared":[127],"SGD":[130],"sampling":[131],"approach":[132,137],"scikit-learn,":[134],"demonstrated":[139],"clear":[141],"advantage":[142]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}