{"id":"https://openalex.org/W3034943024","doi":"https://doi.org/10.1007/s41060-020-00226-0","title":"Streaming statistical models via Merge &amp; Reduce","display_name":"Streaming statistical models via Merge &amp; Reduce","publication_year":2020,"publication_date":"2020-06-12","ids":{"openalex":"https://openalex.org/W3034943024","doi":"https://doi.org/10.1007/s41060-020-00226-0","mag":"3034943024"},"language":"en","primary_location":{"id":"doi:10.1007/s41060-020-00226-0","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s41060-020-00226-0","pdf_url":"https://link.springer.com/content/pdf/10.1007/s41060-020-00226-0.pdf","source":{"id":"https://openalex.org/S4210195017","display_name":"International Journal of Data Science and Analytics","issn_l":"2364-415X","issn":["2364-415X","2364-4168"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319972","host_organization_name":"Springer International Publishing","host_organization_lineage":["https://openalex.org/P4310319972","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer International Publishing","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Data Science and Analytics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s41060-020-00226-0.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5052502058","display_name":"Leo N. Geppert","orcid":null},"institutions":[{"id":"https://openalex.org/I200332995","display_name":"TU Dortmund University","ror":"https://ror.org/01k97gp34","country_code":"DE","type":"education","lineage":["https://openalex.org/I200332995"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Leo N. Geppert","raw_affiliation_strings":["Department of Statistics, Technische Universit\u00e4t Dortmund, 44221, Dortmund, Germany"],"affiliations":[{"raw_affiliation_string":"Department of Statistics, Technische Universit\u00e4t Dortmund, 44221, Dortmund, Germany","institution_ids":["https://openalex.org/I200332995"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063815245","display_name":"Katja Ickstadt","orcid":"https://orcid.org/0000-0001-5157-2496"},"institutions":[{"id":"https://openalex.org/I200332995","display_name":"TU Dortmund University","ror":"https://ror.org/01k97gp34","country_code":"DE","type":"education","lineage":["https://openalex.org/I200332995"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Katja Ickstadt","raw_affiliation_strings":["Department of Statistics, Technische Universit\u00e4t Dortmund, 44221, Dortmund, Germany"],"affiliations":[{"raw_affiliation_string":"Department of Statistics, Technische Universit\u00e4t Dortmund, 44221, Dortmund, Germany","institution_ids":["https://openalex.org/I200332995"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023613530","display_name":"Alexander Munteanu","orcid":"https://orcid.org/0000-0001-6549-3270"},"institutions":[{"id":"https://openalex.org/I200332995","display_name":"TU Dortmund University","ror":"https://ror.org/01k97gp34","country_code":"DE","type":"education","lineage":["https://openalex.org/I200332995"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Alexander Munteanu","raw_affiliation_strings":["Department of Computer Science, Technische Universit\u00e4t Dortmund, 44221, Dortmund, Germany","Department of Statistics, Technische Universit\u00e4t Dortmund, 44221, Dortmund, Germany"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Technische Universit\u00e4t Dortmund, 44221, Dortmund, Germany","institution_ids":["https://openalex.org/I200332995"]},{"raw_affiliation_string":"Department of Statistics, Technische Universit\u00e4t Dortmund, 44221, Dortmund, Germany","institution_ids":["https://openalex.org/I200332995"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034247955","display_name":"Christian Sohler","orcid":"https://orcid.org/0000-0001-8990-3326"},"institutions":[{"id":"https://openalex.org/I180923762","display_name":"University of Cologne","ror":"https://ror.org/00rcxh774","country_code":"DE","type":"education","lineage":["https://openalex.org/I180923762"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Christian Sohler","raw_affiliation_strings":["Institute of Computer Science, The University of Cologne, Weyertal 121, 50931, K\u00f6ln, Germany"],"affiliations":[{"raw_affiliation_string":"Institute of Computer Science, The University of Cologne, Weyertal 121, 50931, K\u00f6ln, Germany","institution_ids":["https://openalex.org/I180923762"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5052502058"],"corresponding_institution_ids":["https://openalex.org/I200332995"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":{"value":2390,"currency":"EUR","value_usd":2990},"fwci":0.7954,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.78035986,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"10","issue":"4","first_page":"331","last_page":"347"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12761","display_name":"Data Stream Mining Techniques","score":0.9988999962806702,"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"}},"topics":[{"id":"https://openalex.org/T12761","display_name":"Data Stream Mining Techniques","score":0.9988999962806702,"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"}},{"id":"https://openalex.org/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.998199999332428,"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"}},{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.9955999851226807,"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/merge","display_name":"Merge (version control)","score":0.8369280695915222},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7541203498840332},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5582836866378784},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5083767771720886},{"id":"https://openalex.org/keywords/statistical-model","display_name":"Statistical model","score":0.4299898147583008},{"id":"https://openalex.org/keywords/bounded-function","display_name":"Bounded function","score":0.4295389652252197},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.42849379777908325},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.40993502736091614},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.33246132731437683},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.23442327976226807},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17646095156669617},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.103658527135849}],"concepts":[{"id":"https://openalex.org/C197129107","wikidata":"https://www.wikidata.org/wiki/Q1921621","display_name":"Merge (version control)","level":2,"score":0.8369280695915222},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7541203498840332},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5582836866378784},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5083767771720886},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.4299898147583008},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.4295389652252197},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.42849379777908325},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.40993502736091614},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.33246132731437683},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23442327976226807},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17646095156669617},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.103658527135849},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s41060-020-00226-0","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s41060-020-00226-0","pdf_url":"https://link.springer.com/content/pdf/10.1007/s41060-020-00226-0.pdf","source":{"id":"https://openalex.org/S4210195017","display_name":"International Journal of Data Science and Analytics","issn_l":"2364-415X","issn":["2364-415X","2364-4168"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319972","host_organization_name":"Springer International Publishing","host_organization_lineage":["https://openalex.org/P4310319972","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer International Publishing","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Data Science and Analytics","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s41060-020-00226-0","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s41060-020-00226-0","pdf_url":"https://link.springer.com/content/pdf/10.1007/s41060-020-00226-0.pdf","source":{"id":"https://openalex.org/S4210195017","display_name":"International Journal of Data Science and Analytics","issn_l":"2364-415X","issn":["2364-415X","2364-4168"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319972","host_organization_name":"Springer International Publishing","host_organization_lineage":["https://openalex.org/P4310319972","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer International Publishing","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Data Science and Analytics","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.4300000071525574,"display_name":"Industry, innovation and infrastructure"}],"awards":[{"id":"https://openalex.org/G2305043180","display_name":null,"funder_award_id":"SFB 876 - C4","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"}],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3034943024.pdf","grobid_xml":"https://content.openalex.org/works/W3034943024.grobid-xml"},"referenced_works_count":58,"referenced_works":["https://openalex.org/W1528905581","https://openalex.org/W1755940714","https://openalex.org/W1899600225","https://openalex.org/W1965972569","https://openalex.org/W1968301997","https://openalex.org/W1969281479","https://openalex.org/W1981313592","https://openalex.org/W1985548569","https://openalex.org/W1987492370","https://openalex.org/W1995484833","https://openalex.org/W1998269045","https://openalex.org/W2006398000","https://openalex.org/W2010371250","https://openalex.org/W2043804332","https://openalex.org/W2045964207","https://openalex.org/W2059651397","https://openalex.org/W2063687049","https://openalex.org/W2096908304","https://openalex.org/W2115709314","https://openalex.org/W2119946100","https://openalex.org/W2125477383","https://openalex.org/W2146200992","https://openalex.org/W2152435742","https://openalex.org/W2157355837","https://openalex.org/W2157754768","https://openalex.org/W2157988812","https://openalex.org/W2160390548","https://openalex.org/W2166368890","https://openalex.org/W2166479660","https://openalex.org/W2229238337","https://openalex.org/W2230030897","https://openalex.org/W2245191586","https://openalex.org/W2405163282","https://openalex.org/W2570048418","https://openalex.org/W2573013575","https://openalex.org/W2755137344","https://openalex.org/W2776050171","https://openalex.org/W2776402781","https://openalex.org/W2788721134","https://openalex.org/W2789144738","https://openalex.org/W2793345127","https://openalex.org/W2805004751","https://openalex.org/W2885062049","https://openalex.org/W2887501547","https://openalex.org/W2947224705","https://openalex.org/W2949910245","https://openalex.org/W2963096809","https://openalex.org/W2963098024","https://openalex.org/W2963977107","https://openalex.org/W2964277272","https://openalex.org/W2964339896","https://openalex.org/W3101466063","https://openalex.org/W3112410551","https://openalex.org/W3175417087","https://openalex.org/W4243936012","https://openalex.org/W4252017042","https://openalex.org/W4253443994","https://openalex.org/W4301861531"],"related_works":["https://openalex.org/W2369673098","https://openalex.org/W2386315983","https://openalex.org/W2158198137","https://openalex.org/W2150276710","https://openalex.org/W2949624407","https://openalex.org/W2035576053","https://openalex.org/W2261692609","https://openalex.org/W3035316584","https://openalex.org/W2396430780","https://openalex.org/W1998138867"],"abstract_inverted_index":{"Abstract":[0],"Merge":[1,80,94,188],"&amp;":[2,81,95,189],"Reduce":[3,82,96,190],"is":[4,18,73,124,158],"a":[5,139,146,176],"general":[6],"algorithmic":[7],"scheme":[8],"in":[9,68,138,153],"the":[10,62,89,93,127,143,180],"theory":[11],"of":[12,32,64,87,126,130,145,183],"data":[13,22,28,53,66,107,112,196],"structures.":[14],"Its":[15],"main":[16],"purpose":[17],"to":[19,44,61,163],"transform":[20],"static":[21],"structures\u2014that":[23,29],"support":[24],"only":[25,159],"queries\u2014into":[26],"dynamic":[27],"allow":[30],"insertions":[31],"new":[33],"elements\u2014with":[34],"as":[35,38],"little":[36],"overhead":[37],"possible.":[39],"This":[40,102],"can":[41],"be":[42],"used":[43],"turn":[45],"classic":[46],"offline":[47],"algorithms":[48],"for":[49,179],"summarizing":[50,88],"and":[51,169,172,194,205],"analyzing":[52],"into":[54,118],"streaming":[55,69],"algorithms.":[56],"We":[57,185],"transfer":[58],"these":[59],"ideas":[60],"setting":[63],"statistical":[65,100,167],"analysis":[67,108],"environments.":[70],"Our":[71],"approach":[72],"conceptually":[74],"different":[75],"from":[76],"previous":[77],"settings":[78],"where":[79],"has":[83],"been":[84],"employed.":[85],"Instead":[86],"data,":[90],"we":[91],"combine":[92],"framework":[97],"directly":[98],"with":[99],"models.":[101,208],"enables":[103],"performing":[104],"computationally":[105],"demanding":[106],"tasks":[109],"on":[110,175,192],"massive":[111],"sets.":[113],"The":[114,134],"computations":[115],"are":[116,136],"divided":[117],"small":[119],"tractable":[120],"batches":[121],"whose":[122],"size":[123],"independent":[125],"total":[128],"number":[129],"observations":[131],"n":[132],".":[133],"results":[135],"combined":[137],"structured":[140],"way":[141],"at":[142],"cost":[144],"bounded":[147],"$$O(\\log":[148],"n)$$":[149],"<mml:math":[150],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"><mml:mrow><mml:mi>O</mml:mi><mml:mo>(</mml:mo><mml:mo>log</mml:mo><mml:mi>n</mml:mi><mml:mo>)</mml:mo></mml:mrow></mml:math>":[151],"factor":[152],"their":[154],"memory":[155],"requirements.":[156],"It":[157],"necessary,":[160],"though":[161],"nontrivial,":[162],"choose":[164],"an":[165],"appropriate":[166],"model":[168],"design":[170],"merge":[171],"reduce":[173],"operations":[174],"casewise":[177],"basis":[178],"specific":[181],"type":[182],"model.":[184],"illustrate":[186],"our":[187],"schemes":[191],"simulated":[193],"real-world":[195],"employing":[197],"(Bayesian)":[198],"linear":[199,207],"regression":[200],"models,":[201],"Gaussian":[202],"mixture":[203],"models":[204],"generalized":[206]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2022,"cited_by_count":4},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}