{"id":"https://openalex.org/W4388118082","doi":"https://doi.org/10.23919/eusipco58844.2023.10289761","title":"Assessment of a Two-Step Integration Method as an Optimizer for Deep Learning","display_name":"Assessment of a Two-Step Integration Method as an Optimizer for Deep Learning","publication_year":2023,"publication_date":"2023-09-04","ids":{"openalex":"https://openalex.org/W4388118082","doi":"https://doi.org/10.23919/eusipco58844.2023.10289761"},"language":"en","primary_location":{"id":"doi:10.23919/eusipco58844.2023.10289761","is_oa":false,"landing_page_url":"http://dx.doi.org/10.23919/eusipco58844.2023.10289761","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 31st European Signal Processing Conference (EUSIPCO)","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/A5077092609","display_name":"Paul Rodr\u00edguez","orcid":"https://orcid.org/0000-0002-8501-0907"},"institutions":[{"id":"https://openalex.org/I65285256","display_name":"Pontificia Universidad Cat\u00f3lica del Per\u00fa","ror":"https://ror.org/00013q465","country_code":"PE","type":"education","lineage":["https://openalex.org/I65285256"]}],"countries":["PE"],"is_corresponding":true,"raw_author_name":"Paul Rodriguez","raw_affiliation_strings":["Pontifical Catholic University of Peru,Department of Electrical Engineering,Lima,Peru","Department of Electrical Engineering, Pontifical Catholic University of Peru, Lima, Peru"],"raw_orcid":"https://orcid.org/0000-0002-8501-0907","affiliations":[{"raw_affiliation_string":"Pontifical Catholic University of Peru,Department of Electrical Engineering,Lima,Peru","institution_ids":["https://openalex.org/I65285256"]},{"raw_affiliation_string":"Department of Electrical Engineering, Pontifical Catholic University of Peru, Lima, Peru","institution_ids":["https://openalex.org/I65285256"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5077092609"],"corresponding_institution_ids":["https://openalex.org/I65285256"],"apc_list":null,"apc_paid":null,"fwci":0.2178,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.46752851,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1245","last_page":"1249"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":1.0,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":1.0,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9998999834060669,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9993000030517578,"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/stochastic-gradient-descent","display_name":"Stochastic gradient descent","score":0.8104021549224854},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6407835483551025},{"id":"https://openalex.org/keywords/acceleration","display_name":"Acceleration","score":0.5612251162528992},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4924653470516205},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4755256474018097},{"id":"https://openalex.org/keywords/balanced-flow","display_name":"Balanced flow","score":0.4246973991394043},{"id":"https://openalex.org/keywords/stochastic-optimization","display_name":"Stochastic optimization","score":0.42466339468955994},{"id":"https://openalex.org/keywords/ball","display_name":"Ball (mathematics)","score":0.4110524654388428},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3715413808822632},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3646319508552551},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.35932663083076477},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.2888469994068146},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2511945068836212}],"concepts":[{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.8104021549224854},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6407835483551025},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.5612251162528992},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4924653470516205},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4755256474018097},{"id":"https://openalex.org/C167879884","wikidata":"https://www.wikidata.org/wiki/Q727568","display_name":"Balanced flow","level":2,"score":0.4246973991394043},{"id":"https://openalex.org/C194387892","wikidata":"https://www.wikidata.org/wiki/Q1747770","display_name":"Stochastic optimization","level":2,"score":0.42466339468955994},{"id":"https://openalex.org/C122041747","wikidata":"https://www.wikidata.org/wiki/Q838611","display_name":"Ball (mathematics)","level":2,"score":0.4110524654388428},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3715413808822632},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3646319508552551},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.35932663083076477},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2888469994068146},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2511945068836212},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"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/C74650414","wikidata":"https://www.wikidata.org/wiki/Q11397","display_name":"Classical mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/eusipco58844.2023.10289761","is_oa":false,"landing_page_url":"http://dx.doi.org/10.23919/eusipco58844.2023.10289761","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 31st European Signal Processing Conference (EUSIPCO)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G253374487","display_name":null,"funder_award_id":"W911NF-22-1-0296","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"}],"funders":[{"id":"https://openalex.org/F4320338281","display_name":"Army Research Office","ror":"https://ror.org/05epdh915"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W6908809","https://openalex.org/W1522301498","https://openalex.org/W1522579744","https://openalex.org/W1543750907","https://openalex.org/W1686810756","https://openalex.org/W1955857676","https://openalex.org/W1988720110","https://openalex.org/W2033493106","https://openalex.org/W2038281434","https://openalex.org/W2146502635","https://openalex.org/W2155677642","https://openalex.org/W2163605009","https://openalex.org/W2523246573","https://openalex.org/W2751905567","https://openalex.org/W2785523195","https://openalex.org/W2896101215","https://openalex.org/W2936995161","https://openalex.org/W2949935872","https://openalex.org/W2964319706","https://openalex.org/W2980149079","https://openalex.org/W3100197791","https://openalex.org/W3102608064","https://openalex.org/W3126775238","https://openalex.org/W3145444543","https://openalex.org/W3175674388","https://openalex.org/W4285801387","https://openalex.org/W6631190155","https://openalex.org/W6637373629","https://openalex.org/W6681435938","https://openalex.org/W6682937675","https://openalex.org/W6684191040","https://openalex.org/W6727249380","https://openalex.org/W6743980561","https://openalex.org/W6747620207","https://openalex.org/W6755977018","https://openalex.org/W6757348626","https://openalex.org/W6757751764","https://openalex.org/W6761030284","https://openalex.org/W6780688020","https://openalex.org/W6784591795","https://openalex.org/W6793164127"],"related_works":["https://openalex.org/W4286899070","https://openalex.org/W4323366756","https://openalex.org/W2913271688","https://openalex.org/W4234593354","https://openalex.org/W2893302333","https://openalex.org/W4285259204","https://openalex.org/W4389775782","https://openalex.org/W3207830353","https://openalex.org/W2963926425","https://openalex.org/W3024083111"],"abstract_inverted_index":{"It":[0],"is":[1,154],"a":[2,32,86,144,158],"known":[3],"fact":[4],"that":[5],"accelerated":[6],"(non-stochastic)":[7],"optimization":[8],"methods":[9,54],"can":[10,25],"be":[11,26],"understood":[12],"as":[13,28,59,62,124,126],"multi-step":[14,52],"integration":[15,34,53,89],"ones:":[16],"e.g.":[17,131],"the":[18,38,43,47,75,92,98,103,149],"heavy":[19],"ball's":[20],"Polyak":[21],"and":[22,122,137],"Nesterov":[23,76],"accelerations":[24],"derived":[27],"particular":[29,64],"instances":[30],"of":[31,49,101],"two-step":[33,87],"method":[35,90,142],"applied":[36],"to":[37,46,83,157],"gradient":[39,69],"flow.":[40],"However,":[41],"in":[42,91],"stochastic":[44,93,129],"context,":[45],"best":[48],"our":[50],"knowledge,":[51],"have":[55],"not":[56],"been":[57],"exploited":[58],"such,":[60],"only":[61],"some":[63],"instances,":[65],"i.e.":[66],"SGD":[67,132],"(stochastic":[68],"descent)":[70],"with":[71,74,134,156],"momentum":[72],"or":[73],"acceleration.":[77],"In":[78],"this":[79],"paper":[80],"we":[81,96],"propose":[82],"directly":[84],"use":[85],"(TS)":[88],"context.":[94],"Furthermore,":[95],"assess":[97],"computational":[99],"effectiveness":[100],"selecting":[102],"TS":[104,140],"method's":[105],"weights":[106],"after":[107],"considering":[108],"its":[109],"lattice":[110],"representation.":[111],"Our":[112],"experiments":[113],"includes":[114],"several":[115,127],"well-known":[116],"multiclass":[117],"classification":[118],"architectures":[119],"(AlexNet,":[120],"VGG16":[121],"EfficientNetV2)":[123],"well":[125],"established":[128],"optimizer":[130],"along":[133],"momentum/Nesterov":[135],"acceleration":[136],"ADAM.":[138,163],"The":[139],"based":[141],"attains":[143],"better":[145],"test":[146],"accuracy":[147],"than":[148],"first":[150],"two,":[151],"whereas":[152],"it":[153],"competitive":[155],"well-tuned":[159],"($\\epsilon":[160],"/$learning":[161],"rate)":[162]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}