{"id":"https://openalex.org/W4406276126","doi":"https://doi.org/10.1109/tsp.2025.3528217","title":"Adaptive Polyak Step-Size for Momentum Accelerated Stochastic Gradient Descent With General Convergence Guarantee","display_name":"Adaptive Polyak Step-Size for Momentum Accelerated Stochastic Gradient Descent With General Convergence Guarantee","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4406276126","doi":"https://doi.org/10.1109/tsp.2025.3528217"},"language":"en","primary_location":{"id":"doi:10.1109/tsp.2025.3528217","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsp.2025.3528217","pdf_url":null,"source":{"id":"https://openalex.org/S168680287","display_name":"IEEE Transactions on Signal Processing","issn_l":"1053-587X","issn":["1053-587X","1941-0476"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Signal Processing","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/A5115845829","display_name":"Jiawei Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiawei Zhang","raw_affiliation_strings":["Department of Electronic Engineering, Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0004-0083-2584","affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Cheng Jin","orcid":"https://orcid.org/0009-0005-4798-1787"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cheng Jin","raw_affiliation_strings":["Department of Electronic Engineering, Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0005-4798-1787","affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100621681","display_name":"Yuantao Gu","orcid":"https://orcid.org/0000-0002-8427-1021"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuantao Gu","raw_affiliation_strings":["Department of Electronic Engineering, Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-8427-1021","affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":4.188,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.93002412,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"73","issue":null,"first_page":"462","last_page":"476"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9908999800682068,"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":0.9908999800682068,"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/T12404","display_name":"Mathematical Approximation and Integration","score":0.9782999753952026,"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"}},{"id":"https://openalex.org/T11716","display_name":"Random Matrices and Applications","score":0.9620000123977661,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"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/convergence","display_name":"Convergence (economics)","score":0.6599841117858887},{"id":"https://openalex.org/keywords/stochastic-gradient-descent","display_name":"Stochastic gradient descent","score":0.625254213809967},{"id":"https://openalex.org/keywords/momentum","display_name":"Momentum (technical analysis)","score":0.5854668617248535},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5157938003540039},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.5110675096511841},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4586164951324463},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.4414274990558624},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.4173985719680786},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.23263466358184814},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.16147509217262268},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.12056806683540344}],"concepts":[{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6599841117858887},{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.625254213809967},{"id":"https://openalex.org/C60718061","wikidata":"https://www.wikidata.org/wiki/Q1414747","display_name":"Momentum (technical analysis)","level":2,"score":0.5854668617248535},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5157938003540039},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.5110675096511841},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4586164951324463},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.4414274990558624},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4173985719680786},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23263466358184814},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.16147509217262268},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.12056806683540344},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tsp.2025.3528217","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsp.2025.3528217","pdf_url":null,"source":{"id":"https://openalex.org/S168680287","display_name":"IEEE Transactions on Signal Processing","issn_l":"1053-587X","issn":["1053-587X","1941-0476"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Signal Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7565187763","display_name":null,"funder_award_id":"U2230201","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W114517082","https://openalex.org/W1522301498","https://openalex.org/W1903029394","https://openalex.org/W2007336860","https://openalex.org/W2020909452","https://openalex.org/W2153635508","https://openalex.org/W2155722796","https://openalex.org/W2194775991","https://openalex.org/W2402144811","https://openalex.org/W2901838001","https://openalex.org/W2963037989","https://openalex.org/W2963433607","https://openalex.org/W2963446712","https://openalex.org/W3196800830","https://openalex.org/W4229680303","https://openalex.org/W4290856730","https://openalex.org/W6631190155","https://openalex.org/W6676105031","https://openalex.org/W6684191040","https://openalex.org/W6705002163","https://openalex.org/W6748389772","https://openalex.org/W6757751764","https://openalex.org/W6762875675","https://openalex.org/W6763249885","https://openalex.org/W6763807091","https://openalex.org/W6766196973","https://openalex.org/W6766978945","https://openalex.org/W6767164110","https://openalex.org/W6774569997","https://openalex.org/W6780688020","https://openalex.org/W6790244998","https://openalex.org/W6790429619","https://openalex.org/W6810038118","https://openalex.org/W6810568334","https://openalex.org/W6810990247","https://openalex.org/W6838944912","https://openalex.org/W6840120808","https://openalex.org/W6849206467","https://openalex.org/W6852730228","https://openalex.org/W6869571195"],"related_works":["https://openalex.org/W4206903459","https://openalex.org/W2754816816","https://openalex.org/W4366280654","https://openalex.org/W3160167280","https://openalex.org/W4231621013","https://openalex.org/W4362706668","https://openalex.org/W3007093918","https://openalex.org/W3008318776","https://openalex.org/W1977633006","https://openalex.org/W1971945429"],"abstract_inverted_index":{"Momentum":[0],"accelerated":[1],"stochastic":[2],"gradient":[3],"descent":[4],"(SGDM)":[5],"has":[6],"gained":[7],"significant":[8],"popularity":[9],"in":[10,110],"several":[11,189],"signal":[12],"processing":[13],"and":[14,34,50,71,122,184],"machine":[15],"learning":[16],"tasks.":[17],"Despite":[18],"its":[19,32,129],"widespread":[20],"success,":[21],"the":[22,44,56,107,114,132,139,162,166],"step":[23,46,62,91,142,158],"size":[24,47,92,143,159],"of":[25,59,117,128,134,165],"SGDM":[26,49,65,145,168],"remains":[27],"a":[28,87,101],"critical":[29],"hyperparameter":[30],"affecting":[31],"performance":[33,186],"often":[35],"requires":[36],"manual":[37],"tuning.":[38],"Recently,":[39],"some":[40],"works":[41],"have":[42],"introduced":[43],"Polyak":[45,61,89,141],"to":[48,68,156,188],"provided":[51],"corresponding":[52],"convergence":[53,57,115,148,182],"analysis.":[54],"However,":[55],"guarantee":[58],"existing":[60],"sizes":[63],"for":[64,75,93,106,119,144],"are":[66],"limited":[67],"convex":[69,121],"objectives":[70],"lack":[72],"theoretical":[73,126,163],"support":[74],"more":[76],"widely":[77],"applicable":[78],"non-convex":[79,123],"problems.":[80],"To":[81,131],"bridge":[82],"this":[83],"gap,":[84],"we":[85,176],"design":[86],"novel":[88],"adaptive":[90],"SGDM.":[94,111],"The":[95],"proposed":[96],"algorithm,":[97],"termed":[98],"SGDM-APS,":[99],"incorporates":[100],"moving":[102],"average":[103],"form":[104],"tailored":[105],"momentum":[108],"mechanism":[109],"We":[112],"establish":[113],"guarantees":[116],"SGDM-APS":[118,137,179],"both":[120],"objectives,":[124],"providing":[125],"analysis":[127,151],"effectiveness.":[130],"best":[133],"our":[135],"knowledge,":[136],"is":[138],"first":[140],"with":[146],"general":[147],"guarantee.":[149],"Our":[150],"can":[152],"also":[153],"be":[154],"extended":[155],"constant":[157],"SGDM,":[160],"enriching":[161],"comprehension":[164],"classic":[167],"algorithm.":[169],"Through":[170],"extensive":[171],"experiments":[172],"on":[173],"diverse":[174],"benchmarks,":[175],"demonstrate":[177],"that":[178],"achieves":[180],"competitive":[181],"rates":[183],"generalization":[185],"compared":[187],"popular":[190],"optimization":[191],"algorithms.":[192]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}