{"id":"https://openalex.org/W2062477158","doi":"https://doi.org/10.1109/bigdata.2014.7004208","title":"Scaling up M-estimation via sampling designs: The Horvitz-Thompson stochastic gradient descent","display_name":"Scaling up M-estimation via sampling designs: The Horvitz-Thompson stochastic gradient descent","publication_year":2014,"publication_date":"2014-10-01","ids":{"openalex":"https://openalex.org/W2062477158","doi":"https://doi.org/10.1109/bigdata.2014.7004208","mag":"2062477158"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata.2014.7004208","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2014.7004208","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Big Data (Big Data)","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/A5088738795","display_name":"St\u00e9phan Cl\u00e9men\u00e7on","orcid":"https://orcid.org/0000-0002-5879-9500"},"institutions":[{"id":"https://openalex.org/I12356871","display_name":"T\u00e9l\u00e9com Paris","ror":"https://ror.org/01naq7912","country_code":"FR","type":"education","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210165912","display_name":"Laboratoire Traitement et Communication de l\u2019Information","ror":"https://ror.org/057er4c39","country_code":"FR","type":"facility","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102","https://openalex.org/I4210165912"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Stephan Clemencon","raw_affiliation_strings":["LTCI UMR","LTCI UMR 5141, T\u00e9l\u00e9com ParisTech & CNRS"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LTCI UMR","institution_ids":["https://openalex.org/I4210165912"]},{"raw_affiliation_string":"LTCI UMR 5141, T\u00e9l\u00e9com ParisTech & CNRS","institution_ids":["https://openalex.org/I4210165912","https://openalex.org/I1294671590","https://openalex.org/I12356871"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086542918","display_name":"Patrice Bertail","orcid":"https://orcid.org/0000-0002-6011-3432"},"institutions":[{"id":"https://openalex.org/I1339876250","display_name":"Institut National de la Statistique et des Etudes Economiques","ror":"https://ror.org/03v6yxf25","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1339876250"]},{"id":"https://openalex.org/I4210102982","display_name":"Centre for Research in Engineering Surface Technology","ror":"https://ror.org/018q3fa22","country_code":"IE","type":"other","lineage":["https://openalex.org/I4210102982"]},{"id":"https://openalex.org/I4210137396","display_name":"Centre de Recherche en \u00c9conomie et Statistique","ror":"https://ror.org/0449khs19","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I142476485","https://openalex.org/I4210108488","https://openalex.org/I4210108488","https://openalex.org/I4210137396","https://openalex.org/I4210145102","https://openalex.org/I4210145102","https://openalex.org/I4210150854","https://openalex.org/I84009706"]}],"countries":["FR","IE"],"is_corresponding":false,"raw_author_name":"Patrice Bertail","raw_affiliation_strings":["Universit\u00e9 Paris-Ouest MODAL'X & CREST - INSEE"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e9 Paris-Ouest MODAL'X & CREST - INSEE","institution_ids":["https://openalex.org/I1339876250","https://openalex.org/I4210137396","https://openalex.org/I4210102982"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052240606","display_name":"Emilie Chautru","orcid":null},"institutions":[{"id":"https://openalex.org/I4210142324","display_name":"CY Cergy Paris Universit\u00e9","ror":"https://ror.org/043htjv09","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210142324"]},{"id":"https://openalex.org/I4210146074","display_name":"Analyse, G\u00e9om\u00e9trie et Mod\u00e9lisation","ror":"https://ror.org/03qgt2624","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I4210141950","https://openalex.org/I4210142324","https://openalex.org/I4210146074"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Emilie Chautru","raw_affiliation_strings":["Universit\u00e9 de Cergy-Pontoise Laboratoire AGM - UMR CNRS","Universit\u00e9 de Cergy-Pontoise Laboratoire AGM - UMR CNRS 8088"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e9 de Cergy-Pontoise Laboratoire AGM - UMR CNRS","institution_ids":["https://openalex.org/I4210146074","https://openalex.org/I4210142324"]},{"raw_affiliation_string":"Universit\u00e9 de Cergy-Pontoise Laboratoire AGM - UMR CNRS 8088","institution_ids":["https://openalex.org/I4210146074","https://openalex.org/I4210142324"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.1145,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.89648254,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"25","last_page":"30"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.9998000264167786,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9998000264167786,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9954000115394592,"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/T10136","display_name":"Statistical Methods and Inference","score":0.9945999979972839,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/stochastic-gradient-descent","display_name":"Stochastic gradient descent","score":0.6765725016593933},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.600432276725769},{"id":"https://openalex.org/keywords/a-priori-and-a-posteriori","display_name":"A priori and a posteriori","score":0.5953896045684814},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.5844249725341797},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5724865794181824},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5624889135360718},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.5264343023300171},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.5070769786834717},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.47519004344940186},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.47503119707107544},{"id":"https://openalex.org/keywords/limit","display_name":"Limit (mathematics)","score":0.4146004617214203},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3853369355201721},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3450716733932495},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.2864498496055603},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1866864562034607},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.09406468272209167}],"concepts":[{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.6765725016593933},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.600432276725769},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.5953896045684814},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.5844249725341797},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5724865794181824},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5624889135360718},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.5264343023300171},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.5070769786834717},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.47519004344940186},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.47503119707107544},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.4146004617214203},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3853369355201721},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3450716733932495},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2864498496055603},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1866864562034607},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.09406468272209167},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/bigdata.2014.7004208","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2014.7004208","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-01707390v1","is_oa":false,"landing_page_url":"https://hal.science/hal-01707390","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Transactions on Big Data, 2015, ⟨10.1109/BigData.2014.7004208⟩","raw_type":"Journal articles"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.8199999928474426}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W594357522","https://openalex.org/W866281365","https://openalex.org/W971128976","https://openalex.org/W1499021337","https://openalex.org/W1543495496","https://openalex.org/W1564947197","https://openalex.org/W1583497301","https://openalex.org/W1810943226","https://openalex.org/W1992832566","https://openalex.org/W2001947543","https://openalex.org/W2007180951","https://openalex.org/W2014902932","https://openalex.org/W2019507167","https://openalex.org/W2021440127","https://openalex.org/W2029966711","https://openalex.org/W2044116626","https://openalex.org/W2051945999","https://openalex.org/W2077563060","https://openalex.org/W2079069670","https://openalex.org/W2102451151","https://openalex.org/W2113651538","https://openalex.org/W2118132743","https://openalex.org/W2127175235","https://openalex.org/W2127684734","https://openalex.org/W2151565294","https://openalex.org/W2155428489","https://openalex.org/W2395349157","https://openalex.org/W2570765347","https://openalex.org/W2946870910","https://openalex.org/W4233471163","https://openalex.org/W4297927014","https://openalex.org/W4298884411","https://openalex.org/W6677106874","https://openalex.org/W6762820410"],"related_works":["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/W2041416246","https://openalex.org/W3020853991","https://openalex.org/W3035836947"],"abstract_inverted_index":{"In":[0],"certain":[1],"situations":[2],"that":[3,22,110],"shall":[4],"be":[5,112],"undoubtedly":[6],"more":[7,9],"and":[8,46],"common":[10],"in":[11,38,42,88,95],"the":[12,16,26,48,57,66,73,106,116,126],"Big":[13],"Data":[14],"era,":[15],"datasets":[17],"available":[18],"are":[19,132],"so":[20],"massive":[21],"computing":[23],"statistics":[24,51],"over":[25],"full":[27],"sample":[28],"is":[29,65],"hardly":[30],"feasible,":[31],"if":[32],"not":[33],"unfeasible.":[34],"A":[35],"natural":[36],"approach":[37],"this":[39,69],"context":[40],"consists":[41],"using":[43],"survey":[44,76],"schemes":[45],"substituting":[47],"\u201cfull":[49],"data\u201d":[50],"with":[52,78,121],"their":[53],"counterparts":[54],"based":[55],"on":[56,82],"resulting":[58],"random":[59],"samples,":[60],"of":[61,68,75,97,108],"manageable":[62],"size.":[63],"It":[64],"purpose":[67],"paper":[70],"to":[71,114],"investigate":[72],"impact":[74],"sampling":[77],"unequal":[79],"inclusion":[80],"probabilities":[81],"(stochastic)":[83],"gradient":[84,117],"descent-based":[85],"M-estimation":[86],"methods":[87],"large-scale":[89],"statistical-learning":[90],"problems.":[91],"We":[92],"prove":[93],"that,":[94],"presence":[96],"some":[98],"a":[99],"priori":[100],"information,":[101],"one":[102],"may":[103],"significantly":[104],"reduce":[105],"number":[107],"terms":[109],"must":[111],"averaged":[113],"estimate":[115],"at":[118],"each":[119],"step":[120],"overwhelming":[122],"probability,":[123],"while":[124],"preserving":[125],"asymptotic":[127],"accuracy.":[128],"These":[129],"striking":[130],"results":[131],"described":[133],"here":[134],"by":[135],"limit":[136],"theorems.":[137]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}