{"id":"https://openalex.org/W2979038540","doi":"https://doi.org/10.1109/ijcnn.2019.8851759","title":"A Count-sketch to Reduce Memory Consumption when Training a Model with Gradient Descent","display_name":"A Count-sketch to Reduce Memory Consumption when Training a Model with Gradient Descent","publication_year":2019,"publication_date":"2019-07-01","ids":{"openalex":"https://openalex.org/W2979038540","doi":"https://doi.org/10.1109/ijcnn.2019.8851759","mag":"2979038540"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn.2019.8851759","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2019.8851759","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Joint Conference on Neural Networks (IJCNN)","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/A5084652478","display_name":"Wissam Siblini","orcid":"https://orcid.org/0000-0002-4193-2061"},"institutions":[{"id":"https://openalex.org/I97188460","display_name":"Nantes Universit\u00e9","ror":"https://ror.org/03gnr7b55","country_code":"FR","type":"education","lineage":["https://openalex.org/I97188460"]},{"id":"https://openalex.org/I4210117005","display_name":"Laboratoire des Sciences du Num\u00e9rique de Nantes","ror":"https://ror.org/02snf8m58","country_code":"FR","type":"facility","lineage":["https://openalex.org/I100445878","https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I205703379","https://openalex.org/I4210117005","https://openalex.org/I4210124215","https://openalex.org/I4210127572","https://openalex.org/I4210139971","https://openalex.org/I97188460","https://openalex.org/I97188460"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Wissam Siblini","raw_affiliation_strings":["Worldline & Univ. of Nantes (LS2N), Lyon, France"],"affiliations":[{"raw_affiliation_string":"Worldline & Univ. of Nantes (LS2N), Lyon, France","institution_ids":["https://openalex.org/I97188460","https://openalex.org/I4210117005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028662508","display_name":"Frank Meyer","orcid":"https://orcid.org/0000-0001-9819-1914"},"institutions":[{"id":"https://openalex.org/I19370010","display_name":"Orange (France)","ror":"https://ror.org/035j0tq82","country_code":"FR","type":"company","lineage":["https://openalex.org/I19370010"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Frank Meyer","raw_affiliation_strings":["Orange Labs, Lannion, France"],"affiliations":[{"raw_affiliation_string":"Orange Labs, Lannion, France","institution_ids":["https://openalex.org/I19370010"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111985039","display_name":"Pascale Kuntz","orcid":null},"institutions":[{"id":"https://openalex.org/I4210117005","display_name":"Laboratoire des Sciences du Num\u00e9rique de Nantes","ror":"https://ror.org/02snf8m58","country_code":"FR","type":"facility","lineage":["https://openalex.org/I100445878","https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I205703379","https://openalex.org/I4210117005","https://openalex.org/I4210124215","https://openalex.org/I4210127572","https://openalex.org/I4210139971","https://openalex.org/I97188460","https://openalex.org/I97188460"]},{"id":"https://openalex.org/I97188460","display_name":"Nantes Universit\u00e9","ror":"https://ror.org/03gnr7b55","country_code":"FR","type":"education","lineage":["https://openalex.org/I97188460"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Pascale Kuntz","raw_affiliation_strings":["Univ. of Nantes (LS2N), Nantes, France"],"affiliations":[{"raw_affiliation_string":"Univ. of Nantes (LS2N), Nantes, France","institution_ids":["https://openalex.org/I4210117005","https://openalex.org/I97188460"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5084652478"],"corresponding_institution_ids":["https://openalex.org/I4210117005","https://openalex.org/I97188460"],"apc_list":null,"apc_paid":null,"fwci":0.14,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.57461964,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"12","issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.9922999739646912,"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/T10320","display_name":"Neural Networks and Applications","score":0.9922999739646912,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9919999837875366,"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"}},{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.978600025177002,"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/sketch","display_name":"Sketch","score":0.763705849647522},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7144397497177124},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.700431764125824},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.5719727873802185},{"id":"https://openalex.org/keywords/consumption","display_name":"Consumption (sociology)","score":0.5313563942909241},{"id":"https://openalex.org/keywords/stochastic-gradient-descent","display_name":"Stochastic gradient descent","score":0.5293781757354736},{"id":"https://openalex.org/keywords/descent","display_name":"Descent (aeronautics)","score":0.5057127475738525},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3871401250362396},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.17606580257415771},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.11385840177536011},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08569714426994324}],"concepts":[{"id":"https://openalex.org/C2779231336","wikidata":"https://www.wikidata.org/wiki/Q7534724","display_name":"Sketch","level":2,"score":0.763705849647522},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7144397497177124},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.700431764125824},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.5719727873802185},{"id":"https://openalex.org/C30772137","wikidata":"https://www.wikidata.org/wiki/Q5164762","display_name":"Consumption (sociology)","level":2,"score":0.5313563942909241},{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.5293781757354736},{"id":"https://openalex.org/C2776637919","wikidata":"https://www.wikidata.org/wiki/Q624380","display_name":"Descent (aeronautics)","level":2,"score":0.5057127475738525},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3871401250362396},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.17606580257415771},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.11385840177536011},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08569714426994324},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/ijcnn.2019.8851759","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2019.8851759","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-02539058v1","is_oa":false,"landing_page_url":"https://hal.science/hal-02539058","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":"International Joint Conference on Neural Networks (IJCNN), Jul 2019, Budapest, Hungary. &#x27E8;10.1109/ijcnn.2019.8851759&#x27E9;","raw_type":"Conference papers"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W21938781","https://openalex.org/W114517082","https://openalex.org/W756166754","https://openalex.org/W1493892051","https://openalex.org/W1524416683","https://openalex.org/W1965972569","https://openalex.org/W1966948031","https://openalex.org/W1976709621","https://openalex.org/W1994616650","https://openalex.org/W1995484833","https://openalex.org/W1996268356","https://openalex.org/W2018989507","https://openalex.org/W2037757210","https://openalex.org/W2040708309","https://openalex.org/W2048266589","https://openalex.org/W2068074736","https://openalex.org/W2070996757","https://openalex.org/W2080234606","https://openalex.org/W2089497633","https://openalex.org/W2097665501","https://openalex.org/W2137107481","https://openalex.org/W2145065594","https://openalex.org/W2183087644","https://openalex.org/W2187483593","https://openalex.org/W2520348554","https://openalex.org/W2616732338","https://openalex.org/W2732039841","https://openalex.org/W2732951378","https://openalex.org/W2743021690","https://openalex.org/W2752618134","https://openalex.org/W2788125153","https://openalex.org/W2886305600","https://openalex.org/W2963745697","https://openalex.org/W3008214279","https://openalex.org/W3103298265","https://openalex.org/W4249843299","https://openalex.org/W4297817021","https://openalex.org/W6600882167","https://openalex.org/W6622240820","https://openalex.org/W6631445940","https://openalex.org/W6674684338","https://openalex.org/W6680483772","https://openalex.org/W6685974025","https://openalex.org/W6686785280","https://openalex.org/W6740159687","https://openalex.org/W6740697456","https://openalex.org/W6744170582","https://openalex.org/W6753458378"],"related_works":["https://openalex.org/W4206903459","https://openalex.org/W2754816816","https://openalex.org/W4366280654","https://openalex.org/W3160167280","https://openalex.org/W4362706668","https://openalex.org/W4231621013","https://openalex.org/W2015288657","https://openalex.org/W3171021120","https://openalex.org/W3008318776","https://openalex.org/W2041416246"],"abstract_inverted_index":{"Training":[0],"machine":[1],"learning":[2],"models":[3,182],"requires":[4],"the":[5,31,43,81,90,93,105,110,132,139,144,152,164,168],"storage":[6,134,142],"of":[7,12,70,92,109,126,135,146,154],"an":[8],"ever-growing":[9],"number":[10],"n":[11,73],"parameters,":[13],"which":[14],"leads":[15],"to":[16,28,123,158,177,183,188,190],"memory":[17,155],"management":[18],"issues.":[19],"In":[20,170],"this":[21,172],"paper,":[22],"we":[23],"propose":[24],"a":[25,175],"novel":[26],"approach":[27],"accurately":[29],"estimate":[30],"largest":[32],"parameters":[33,137],"sufficient":[34],"for":[35,114],"prediction":[36],"tasks":[37],"while":[38,149],"saving":[39],"memory.":[40],"Inspired":[41],"by":[42,75,89],"heavy":[44],"hitter":[45],"identification":[46],"problem":[47,113],"in":[48,57,80,96],"data":[49],"stream":[50],"analysis,":[51],"our":[52],"count-sketch":[53,141],"based":[54],"strategy":[55],"consists":[56],"independently":[58],"storing":[59],"t":[60,98],"~":[61],"10":[62],"times":[63],"all":[64,136],"parameter":[65,85],"values":[66,79,94],"on":[67,104,163],"different":[68],"sets":[69],"r":[71],"<;<;":[72],"counters":[74],"randomly":[76],"aggregating":[77],"several":[78,178],"same":[82],"counters.":[83,100],"Each":[84],"is":[86],"then":[87],"approximated":[88],"median":[91],"stored":[95],"its":[97],"associated":[99],"We":[101],"conduct":[102],"experiments":[103],"popular":[106],"use":[107,153],"case":[108],"linear":[111],"regression":[112],"nine":[115],"multi-label":[116],"datasets":[117],"inducing":[118],"various":[119],"model":[120],"sizes":[121],"(up":[122],"11.7":[124],"GB":[125],"RAM).":[127],"It":[128],"shows":[129],"that":[130],"replacing":[131],"regular":[133],"with":[138],"proposed":[140],"preserves":[143],"quality":[145],"predictive":[147],"performances":[148],"significantly":[150],"reducing":[151],"(from":[156],"80%":[157],"99.9%).":[159],"A":[160],"theoretical":[161],"bound":[162],"approximation":[165],"error":[166],"completes":[167],"experiments.":[169],"practice,":[171],"work":[173],"gives":[174],"chance":[176],"potentially":[179],"interesting":[180],"memory-hungry":[181],"be":[184],"implemented":[185],"without":[186],"having":[187],"resort":[189],"costly":[191],"computational":[192],"environments.":[193]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}