{"id":"https://openalex.org/W4410258070","doi":"https://doi.org/10.1007/s00521-025-11220-7","title":"Using adaptive learning and momentum to improve generalization","display_name":"Using adaptive learning and momentum to improve generalization","publication_year":2025,"publication_date":"2025-05-10","ids":{"openalex":"https://openalex.org/W4410258070","doi":"https://doi.org/10.1007/s00521-025-11220-7"},"language":"en","primary_location":{"id":"doi:10.1007/s00521-025-11220-7","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00521-025-11220-7","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00521-025-11220-7.pdf","source":{"id":"https://openalex.org/S147897268","display_name":"Neural Computing and Applications","issn_l":"0941-0643","issn":["0941-0643","1433-3058"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Computing and Applications","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s00521-025-11220-7.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5080248140","display_name":"Usman Anjum","orcid":"https://orcid.org/0000-0002-9280-772X"},"institutions":[{"id":"https://openalex.org/I63135867","display_name":"University of Cincinnati","ror":"https://ror.org/01e3m7079","country_code":"US","type":"education","lineage":["https://openalex.org/I63135867"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Usman Anjum","raw_affiliation_strings":["Department of Computer Science, University of Cincinnati, 2851 Woodside Drive, Cincinnati, Ohio, 100190, USA"],"raw_orcid":"https://orcid.org/0000-0002-9280-772X","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Cincinnati, 2851 Woodside Drive, Cincinnati, Ohio, 100190, USA","institution_ids":["https://openalex.org/I63135867"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Chris Stockman","orcid":null},"institutions":[{"id":"https://openalex.org/I63135867","display_name":"University of Cincinnati","ror":"https://ror.org/01e3m7079","country_code":"US","type":"education","lineage":["https://openalex.org/I63135867"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Chris Stockman","raw_affiliation_strings":["Department of Computer Science, University of Cincinnati, 2851 Woodside Drive, Cincinnati, Ohio, 100190, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Cincinnati, 2851 Woodside Drive, Cincinnati, Ohio, 100190, USA","institution_ids":["https://openalex.org/I63135867"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075411396","display_name":"Cat Luong","orcid":"https://orcid.org/0009-0001-5771-7470"},"institutions":[{"id":"https://openalex.org/I63135867","display_name":"University of Cincinnati","ror":"https://ror.org/01e3m7079","country_code":"US","type":"education","lineage":["https://openalex.org/I63135867"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cat Luong","raw_affiliation_strings":["Department of Computer Science, University of Cincinnati, 2851 Woodside Drive, Cincinnati, Ohio, 100190, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Cincinnati, 2851 Woodside Drive, Cincinnati, Ohio, 100190, USA","institution_ids":["https://openalex.org/I63135867"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102301059","display_name":"Felix Zhan","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Felix Zhan","raw_affiliation_strings":["Department of Computer Science, Stanford University, Stanford, California, 94305, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Stanford University, Stanford, California, 94305, USA","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5080248140"],"corresponding_institution_ids":["https://openalex.org/I63135867"],"apc_list":{"value":2990,"currency":"USD","value_usd":2990},"apc_paid":{"value":2990,"currency":"USD","value_usd":2990},"fwci":2.5289,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.89793491,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":"37","issue":"19","first_page":"14399","last_page":"14426"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","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/T11612","display_name":"Stochastic Gradient Optimization Techniques","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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9987999796867371,"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/T12676","display_name":"Machine Learning and ELM","score":0.9979000091552734,"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/computational-science-and-engineering","display_name":"Computational Science and Engineering","score":0.8244456052780151},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6976116895675659},{"id":"https://openalex.org/keywords/momentum","display_name":"Momentum (technical analysis)","score":0.6249878406524658},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5918130874633789},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4226161241531372},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.38173893094062805},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35952818393707275},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2991281747817993},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.1427401602268219},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.06746348738670349}],"concepts":[{"id":"https://openalex.org/C68597687","wikidata":"https://www.wikidata.org/wiki/Q362601","display_name":"Computational Science and Engineering","level":2,"score":0.8244456052780151},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6976116895675659},{"id":"https://openalex.org/C60718061","wikidata":"https://www.wikidata.org/wiki/Q1414747","display_name":"Momentum (technical analysis)","level":2,"score":0.6249878406524658},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5918130874633789},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4226161241531372},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.38173893094062805},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35952818393707275},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2991281747817993},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.1427401602268219},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.06746348738670349},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s00521-025-11220-7","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00521-025-11220-7","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00521-025-11220-7.pdf","source":{"id":"https://openalex.org/S147897268","display_name":"Neural Computing and Applications","issn_l":"0941-0643","issn":["0941-0643","1433-3058"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Computing and Applications","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s00521-025-11220-7","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00521-025-11220-7","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00521-025-11220-7.pdf","source":{"id":"https://openalex.org/S147897268","display_name":"Neural Computing and Applications","issn_l":"0941-0643","issn":["0941-0643","1433-3058"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Computing and Applications","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4841390714","display_name":null,"funder_award_id":"N00014-23-1-2396","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G5479835431","display_name":"Beginnings: Establishing an Experiential Learning Pathway in Artificial Intelligence","funder_award_id":"2346609","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8150659101","display_name":"Proto-OKN Theme 1: The Water-Energy Nexus Open Knowledge Network (WEN-OKN)","funder_award_id":"2333726","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8876996369","display_name":null,"funder_award_id":"N00014","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306078","display_name":"U.S. Department of Defense","ror":"https://ror.org/0447fe631"},{"id":"https://openalex.org/F4320309575","display_name":"Cincinnati Children's Hospital Medical Center","ror":"https://ror.org/01hcyya48"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4410258070.pdf","grobid_xml":"https://content.openalex.org/works/W4410258070.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W99485931","https://openalex.org/W1988720110","https://openalex.org/W2089217417","https://openalex.org/W2127447444","https://openalex.org/W2548982044","https://openalex.org/W2963433607","https://openalex.org/W3023119660","https://openalex.org/W3081534675","https://openalex.org/W3141595720","https://openalex.org/W4229075175","https://openalex.org/W4318147828","https://openalex.org/W4385346229","https://openalex.org/W4386066238","https://openalex.org/W4388116480","https://openalex.org/W4391361008","https://openalex.org/W4393153991","https://openalex.org/W4399432515","https://openalex.org/W4401863877","https://openalex.org/W4402716202","https://openalex.org/W4402923252","https://openalex.org/W4403527779","https://openalex.org/W4407403550","https://openalex.org/W6600007113","https://openalex.org/W6601676141","https://openalex.org/W6602696911","https://openalex.org/W6605299328","https://openalex.org/W6606467459"],"related_works":["https://openalex.org/W3162204513","https://openalex.org/W2371138613","https://openalex.org/W2048963458","https://openalex.org/W43109613","https://openalex.org/W2359952343","https://openalex.org/W2239445980","https://openalex.org/W4393232657","https://openalex.org/W2080152487","https://openalex.org/W3083152911","https://openalex.org/W3022347918"],"abstract_inverted_index":{"Abstract":[0],"In":[1],"this":[2],"paper,":[3],"we":[4],"propose":[5],"a":[6],"novel":[7],"algorithm":[8],"called":[9],"adaptive":[10,27],"learning":[11,28],"&":[12],"momentum":[13,30],"sharpness-aware":[14,24],"minimization":[15,25],"MAML":[16],"(AS-MAML)":[17],"that":[18,44],"builds":[19],"upon":[20],"the":[21,49,57],"concept":[22],"of":[23],"and":[26,29,41],"to":[31],"improve":[32],"generalization.":[33],"We":[34,55],"prove":[35],"theoretically":[36],"by":[37],"performing":[38],"convergence":[39],"analysis":[40,43,63],"PAC-Bayes":[42],"AS-MAML":[45],"performs":[46],"better":[47],"than":[48],"state-of-the-art":[50],"algorithms":[51],"in":[52],"model-agnostic":[53],"meta-learning.":[54],"draw":[56],"same":[58],"conclusion":[59],"through":[60],"extensive":[61],"experimental":[62],"using":[64],"benchmark":[65],"datasets.":[66]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}