{"id":"https://openalex.org/W4312589547","doi":"https://doi.org/10.1134/s00051179220100071","title":"Gradient Methods for Optimizing Metaparameters in the Knowledge Distillation Problem","display_name":"Gradient Methods for Optimizing Metaparameters in the Knowledge Distillation Problem","publication_year":2022,"publication_date":"2022-10-01","ids":{"openalex":"https://openalex.org/W4312589547","doi":"https://doi.org/10.1134/s00051179220100071"},"language":"en","primary_location":{"id":"doi:10.1134/s00051179220100071","is_oa":false,"landing_page_url":"https://doi.org/10.1134/s00051179220100071","pdf_url":null,"source":{"id":"https://openalex.org/S134188425","display_name":"Automation and Remote Control","issn_l":"0005-1179","issn":["0005-1179","1608-3032"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320267","host_organization_name":"Pleiades Publishing","host_organization_lineage":["https://openalex.org/P4310320267","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Pleiades Publishing","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Automation and Remote Control","raw_type":"journal-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/A5015328242","display_name":"M. Gorpinich","orcid":null},"institutions":[{"id":"https://openalex.org/I153845743","display_name":"Moscow Institute of Physics and Technology","ror":"https://ror.org/00v0z9322","country_code":"RU","type":"education","lineage":["https://openalex.org/I153845743"]}],"countries":["RU"],"is_corresponding":true,"raw_author_name":"M. Gorpinich","raw_affiliation_strings":["Moscow Institute of Physics and Technology, Dolgoprudnyi, Moscow oblast, 141701, Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Moscow Institute of Physics and Technology, Dolgoprudnyi, Moscow oblast, 141701, Russia","institution_ids":["https://openalex.org/I153845743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010405643","display_name":"Oleg Bakhteev","orcid":"https://orcid.org/0000-0002-6497-3667"},"institutions":[{"id":"https://openalex.org/I2801535751","display_name":"Dorodnitsyn Computing Centre","ror":"https://ror.org/01vgda714","country_code":"RU","type":"facility","lineage":["https://openalex.org/I1313323035","https://openalex.org/I2801535751","https://openalex.org/I4210124601"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"O. Yu. Bakhteev","raw_affiliation_strings":["Dorodnicyn Computing Centre, Russian Academy of Sciences, Moscow, 119333, Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dorodnicyn Computing Centre, Russian Academy of Sciences, Moscow, 119333, Russia","institution_ids":["https://openalex.org/I2801535751"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039361307","display_name":"Vadim Strijov","orcid":"https://orcid.org/0000-0002-2194-8859"},"institutions":[{"id":"https://openalex.org/I2801535751","display_name":"Dorodnitsyn Computing Centre","ror":"https://ror.org/01vgda714","country_code":"RU","type":"facility","lineage":["https://openalex.org/I1313323035","https://openalex.org/I2801535751","https://openalex.org/I4210124601"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"V. V. Strijov","raw_affiliation_strings":["Dorodnicyn Computing Centre, Russian Academy of Sciences, Moscow, 119333, Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dorodnicyn Computing Centre, Russian Academy of Sciences, Moscow, 119333, Russia","institution_ids":["https://openalex.org/I2801535751"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5015328242"],"corresponding_institution_ids":["https://openalex.org/I153845743"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.15098042,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"83","issue":"10","first_page":"1544","last_page":"1554"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9987000226974487,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9987000226974487,"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/T10320","display_name":"Neural Networks and Applications","score":0.9983999729156494,"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/T12111","display_name":"Industrial Vision Systems and Defect Detection","score":0.9919000267982483,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.8120860457420349},{"id":"https://openalex.org/keywords/mnist-database","display_name":"MNIST database","score":0.5800430774688721},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5670372843742371},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5229302644729614},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5010819435119629},{"id":"https://openalex.org/keywords/optimization-problem","display_name":"Optimization problem","score":0.4832811653614044},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4543946087360382},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.4394882023334503},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3508409261703491},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3265841007232666},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2638673484325409},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.22652652859687805},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.08491471409797668}],"concepts":[{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.8120860457420349},{"id":"https://openalex.org/C190502265","wikidata":"https://www.wikidata.org/wiki/Q17069496","display_name":"MNIST database","level":3,"score":0.5800430774688721},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5670372843742371},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5229302644729614},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5010819435119629},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.4832811653614044},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4543946087360382},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.4394882023334503},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3508409261703491},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3265841007232666},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2638673484325409},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.22652652859687805},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.08491471409797668},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1134/s00051179220100071","is_oa":false,"landing_page_url":"https://doi.org/10.1134/s00051179220100071","pdf_url":null,"source":{"id":"https://openalex.org/S134188425","display_name":"Automation and Remote Control","issn_l":"0005-1179","issn":["0005-1179","1608-3032"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320267","host_organization_name":"Pleiades Publishing","host_organization_lineage":["https://openalex.org/P4310320267","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Pleiades Publishing","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Automation and Remote Control","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W2948308156","https://openalex.org/W2964103341","https://openalex.org/W3035163969","https://openalex.org/W3081168214","https://openalex.org/W3118608800","https://openalex.org/W6600669965","https://openalex.org/W6813649573"],"related_works":["https://openalex.org/W2950475743","https://openalex.org/W4386603768","https://openalex.org/W2886711096","https://openalex.org/W4380078352","https://openalex.org/W3046591097","https://openalex.org/W2590796488","https://openalex.org/W2734358244","https://openalex.org/W2750384547","https://openalex.org/W2809732489","https://openalex.org/W3088091256"],"abstract_inverted_index":{"The":[0,45,73,114,152],"paper":[1,46],"investigates":[2],"the":[3,51,55,66,69,81,84,88,91,94,98,105,117,126,133,136],"distillation":[4,11,52,70,106],"problem":[5,16,53,79,119],"for":[6,54,76],"deep":[7],"learning":[8],"models.":[9],"Knowledge":[10],"is":[12,32,80,109,141,147,155],"a":[13,21,24,29,35,38,42,48,78,110,158],"metaparameter":[14,127],"optimization":[15,58,71,118,138],"in":[17],"which":[18],"information":[19],"from":[20],"model":[22,36,96],"of":[23,37,50,57,59,68,83,93,116,132,135,139],"more":[25],"complex":[26],"structure,":[27,40],"called":[28,41],"teacher":[30,99],"model,":[31],"transferred":[33],"to":[34,104,124],"simpler":[39],"student":[43,95],"model.":[44,100],"proposes":[47],"generalization":[49],"case":[56],"metaparameters":[60,103,140],"by":[61],"gradient":[62,137],"methods.":[63],"Metaparameters":[64],"are":[65,120],"parameters":[67],"problem.":[72],"loss":[74,107],"function":[75,108],"such":[77],"sum":[82],"classification":[85],"term":[86],"and":[87,97,144,163],"cross-entropy":[89],"between":[90],"responses":[92],"Assigning":[101],"optimal":[102],"computationally":[111],"difficult":[112],"task.":[113],"properties":[115],"investigated":[121],"so":[122],"as":[123,166,168],"predict":[125],"update":[128],"trajectory.":[129],"An":[130],"analysis":[131],"trajectory":[134],"carried":[142],"out,":[143],"their":[145],"value":[146],"predicted":[148],"using":[149,157],"linear":[150],"functions.":[151],"proposed":[153],"approach":[154],"illustrated":[156],"computational":[159],"experiment":[160],"on":[161,169],"CIFAR-10":[162],"Fashion-MNIST":[164],"samples":[165],"well":[167],"synthetic":[170],"data.":[171]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}