{"id":"https://openalex.org/W2473611539","doi":"https://doi.org/10.1109/ijcnn.2017.7966082","title":"Nesterov's accelerated gradient and momentum as approximations to regularised update descent","display_name":"Nesterov's accelerated gradient and momentum as approximations to regularised update descent","publication_year":2017,"publication_date":"2017-05-01","ids":{"openalex":"https://openalex.org/W2473611539","doi":"https://doi.org/10.1109/ijcnn.2017.7966082","mag":"2473611539"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn.2017.7966082","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2017.7966082","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1607.01981","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5067684042","display_name":"Aleksandar Botev","orcid":"https://orcid.org/0000-0001-9021-1124"},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Aleksandar Botev","raw_affiliation_strings":["Department of Computer Science, University College, London","(Department of Computer Science, University College, London)"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University College, London","institution_ids":["https://openalex.org/I45129253"]},{"raw_affiliation_string":"(Department of Computer Science, University College, London)","institution_ids":["https://openalex.org/I45129253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031943811","display_name":"Guy Lever","orcid":"https://orcid.org/0000-0001-9551-1839"},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Guy Lever","raw_affiliation_strings":["Department of Computer Science, University College, London","(Department of Computer Science, University College, London)"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University College, London","institution_ids":["https://openalex.org/I45129253"]},{"raw_affiliation_string":"(Department of Computer Science, University College, London)","institution_ids":["https://openalex.org/I45129253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101763101","display_name":"David Barber","orcid":"https://orcid.org/0000-0003-2163-2982"},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]},{"id":"https://openalex.org/I4210128584","display_name":"The Alan Turing Institute","ror":"https://ror.org/035dkdb55","country_code":"GB","type":"facility","lineage":["https://openalex.org/I4210128584"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"David Barber","raw_affiliation_strings":["Department of Computer Science, Alan Turing Institute, London","Department of Computer Science, University College London, Alan Turing Institute"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Alan Turing Institute, London","institution_ids":["https://openalex.org/I4210128584"]},{"raw_affiliation_string":"Department of Computer Science, University College London, Alan Turing Institute","institution_ids":["https://openalex.org/I4210128584","https://openalex.org/I45129253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5067684042"],"corresponding_institution_ids":["https://openalex.org/I45129253"],"apc_list":null,"apc_paid":null,"fwci":2.7001,"has_fulltext":true,"cited_by_count":18,"citation_normalized_percentile":{"value":0.92076602,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1899","last_page":"1903"},"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/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10963","display_name":"Advanced Optimization Algorithms Research","score":0.9976999759674072,"subfield":{"id":"https://openalex.org/subfields/2612","display_name":"Numerical Analysis"},"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/gradient-descent","display_name":"Gradient descent","score":0.7422487735748291},{"id":"https://openalex.org/keywords/momentum","display_name":"Momentum (technical analysis)","score":0.6831732988357544},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.5599023103713989},{"id":"https://openalex.org/keywords/proximal-gradient-methods","display_name":"Proximal Gradient Methods","score":0.5047277212142944},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.48929283022880554},{"id":"https://openalex.org/keywords/interpretation","display_name":"Interpretation (philosophy)","score":0.48291918635368347},{"id":"https://openalex.org/keywords/gradient-method","display_name":"Gradient method","score":0.4750354588031769},{"id":"https://openalex.org/keywords/descent","display_name":"Descent (aeronautics)","score":0.463474839925766},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.45034781098365784},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4442068636417389},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.43765005469322205},{"id":"https://openalex.org/keywords/stochastic-gradient-descent","display_name":"Stochastic gradient descent","score":0.4359573423862457},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3775050640106201},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.2273150384426117},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.22401002049446106},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.09322592616081238},{"id":"https://openalex.org/keywords/quantum-mechanics","display_name":"Quantum mechanics","score":0.060417234897613525}],"concepts":[{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.7422487735748291},{"id":"https://openalex.org/C60718061","wikidata":"https://www.wikidata.org/wiki/Q1414747","display_name":"Momentum (technical analysis)","level":2,"score":0.6831732988357544},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.5599023103713989},{"id":"https://openalex.org/C10494615","wikidata":"https://www.wikidata.org/wiki/Q17086765","display_name":"Proximal Gradient Methods","level":4,"score":0.5047277212142944},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.48929283022880554},{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.48291918635368347},{"id":"https://openalex.org/C115680565","wikidata":"https://www.wikidata.org/wiki/Q5977448","display_name":"Gradient method","level":2,"score":0.4750354588031769},{"id":"https://openalex.org/C2776637919","wikidata":"https://www.wikidata.org/wiki/Q624380","display_name":"Descent (aeronautics)","level":2,"score":0.463474839925766},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.45034781098365784},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4442068636417389},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.43765005469322205},{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.4359573423862457},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3775050640106201},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.2273150384426117},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.22401002049446106},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.09322592616081238},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.060417234897613525},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/ijcnn.2017.7966082","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2017.7966082","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1607.01981","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1607.01981","pdf_url":"https://arxiv.org/pdf/1607.01981","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:eprints.ucl.ac.uk.OAI2:10062712","is_oa":true,"landing_page_url":"https://discovery.ucl.ac.uk/id/eprint/10062712/","pdf_url":"https://discovery.ucl.ac.uk/10062712/1/07966082.pdf","source":{"id":"https://openalex.org/S4306400024","display_name":"UCL Discovery (University College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I45129253","host_organization_name":"University College London","host_organization_lineage":["https://openalex.org/I45129253"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"     In:  Proceedings of the 2017 International Joint Conference on Neural Networks (IJCNN).    IEEE: Anchorage, AK, USA. (2017)     ","raw_type":"Proceedings paper"},{"id":"mag:2473611539","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1607.01981.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1607.01981","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1607.01981","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1607.01981","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1607.01981","pdf_url":"https://arxiv.org/pdf/1607.01981","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W104184427","https://openalex.org/W1551029929","https://openalex.org/W1980287119","https://openalex.org/W2100495367","https://openalex.org/W2101368829","https://openalex.org/W3029645440","https://openalex.org/W6604254268","https://openalex.org/W6761030284"],"related_works":["https://openalex.org/W2964159641","https://openalex.org/W2969466692","https://openalex.org/W2963607709","https://openalex.org/W2988137070","https://openalex.org/W2971697083","https://openalex.org/W2996271651","https://openalex.org/W2908564467","https://openalex.org/W2294200672","https://openalex.org/W2951696961","https://openalex.org/W2766514582","https://openalex.org/W2000656810","https://openalex.org/W3103518151","https://openalex.org/W3197743078","https://openalex.org/W2964045956","https://openalex.org/W2106164382","https://openalex.org/W2963541115","https://openalex.org/W3198463092","https://openalex.org/W2963003090","https://openalex.org/W2947038353","https://openalex.org/W2962895241"],"abstract_inverted_index":{"We":[0,37],"present":[1],"a":[2,29,40],"unifying":[3],"framework":[4],"for":[5],"adapting":[6],"the":[7,34,58],"update":[8],"direction":[9],"in":[10],"gradient-based":[11],"iterative":[12],"optimization":[13],"methods.":[14],"As":[15],"natural":[16],"special":[17],"cases":[18],"we":[19,44],"re-derive":[20],"classical":[21,59],"momentum":[22,60],"and":[23],"Nesterov's":[24,55],"accelerated":[25],"gradient":[26],"method,":[27],"lending":[28],"new":[30,41],"intuitive":[31],"interpretation":[32],"to":[33],"latter":[35],"algorithm.":[36,61],"show":[38],"that":[39],"algorithm,":[42],"which":[43],"term":[45],"Regularised":[46],"Gradient":[47],"Descent,":[48],"can":[49],"converge":[50],"more":[51],"quickly":[52],"than":[53],"either":[54],"algorithm":[56],"or":[57]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":5}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}