{"id":"https://openalex.org/W4411801007","doi":"https://doi.org/10.61822/amcs-2025-0018","title":"The generalization error bound for a stochastic gradient descent family via a Gaussian approximation method","display_name":"The generalization error bound for a stochastic gradient descent family via a Gaussian approximation method","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4411801007","doi":"https://doi.org/10.61822/amcs-2025-0018"},"language":"en","primary_location":{"id":"doi:10.61822/amcs-2025-0018","is_oa":true,"landing_page_url":"https://doi.org/10.61822/amcs-2025-0018","pdf_url":null,"source":{"id":"https://openalex.org/S117679522","display_name":"International Journal of Applied Mathematics and Computer Science","issn_l":"1641-876X","issn":["1641-876X","2083-8492"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320322","host_organization_name":"De Gruyter Open","host_organization_lineage":["https://openalex.org/P4310320322","https://openalex.org/P4310313990"],"host_organization_lineage_names":["De Gruyter Open","De Gruyter"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Applied Mathematics and Computer Science","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.61822/amcs-2025-0018","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100353534","display_name":"Hao Chen","orcid":"https://orcid.org/0000-0002-2848-8912"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hao Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024602088","display_name":"Zhanfeng Mo","orcid":"https://orcid.org/0000-0003-2254-8651"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhanfeng Mo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5047580521","display_name":"Zhouwang Yang","orcid":"https://orcid.org/0000-0002-9454-9146"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhouwang Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":4080,"currency":"PLN","value_usd":1100},"apc_paid":{"value":4080,"currency":"PLN","value_usd":1100},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.07258256,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"35","issue":"2","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9628000259399414,"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":0.9628000259399414,"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/T12056","display_name":"Markov Chains and Monte Carlo Methods","score":0.9373000264167786,"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"}},{"id":"https://openalex.org/T12404","display_name":"Mathematical Approximation and Integration","score":0.9185000061988831,"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/generalization","display_name":"Generalization","score":0.7771258354187012},{"id":"https://openalex.org/keywords/stochastic-gradient-descent","display_name":"Stochastic gradient descent","score":0.65520179271698},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.6319996118545532},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.608799159526825},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.563669741153717},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.5290754437446594},{"id":"https://openalex.org/keywords/generalization-error","display_name":"Generalization error","score":0.4925990700721741},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.36435407400131226},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.2914164662361145},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.27081364393234253},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.16912922263145447},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.10501936078071594},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.09083962440490723},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.0675758421421051},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.04871422052383423}],"concepts":[{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.7771258354187012},{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.65520179271698},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.6319996118545532},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.608799159526825},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.563669741153717},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.5290754437446594},{"id":"https://openalex.org/C117765406","wikidata":"https://www.wikidata.org/wiki/Q5362437","display_name":"Generalization error","level":3,"score":0.4925990700721741},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.36435407400131226},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.2914164662361145},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.27081364393234253},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.16912922263145447},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.10501936078071594},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.09083962440490723},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.0675758421421051},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.04871422052383423},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.61822/amcs-2025-0018","is_oa":true,"landing_page_url":"https://doi.org/10.61822/amcs-2025-0018","pdf_url":null,"source":{"id":"https://openalex.org/S117679522","display_name":"International Journal of Applied Mathematics and Computer Science","issn_l":"1641-876X","issn":["1641-876X","2083-8492"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320322","host_organization_name":"De Gruyter Open","host_organization_lineage":["https://openalex.org/P4310320322","https://openalex.org/P4310313990"],"host_organization_lineage_names":["De Gruyter Open","De Gruyter"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Applied Mathematics and Computer Science","raw_type":"journal-article"},{"id":"pmh:oai:dr.ntu.edu.sg:10356/207287","is_oa":true,"landing_page_url":"https://hdl.handle.net/10356/207287","pdf_url":null,"source":{"id":"https://openalex.org/S4306402609","display_name":"DR-NTU (Nanyang Technological University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I172675005","host_organization_name":"Nanyang Technological University","host_organization_lineage":["https://openalex.org/I172675005"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"Journal Article"},{"id":"pmh:oai:doaj.org/article:b6af085ee11d4c059699cb43c8687641","is_oa":true,"landing_page_url":"https://doaj.org/article/b6af085ee11d4c059699cb43c8687641","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"International Journal of Applied Mathematics and Computer Science, Vol 35, Iss 2, Pp 251-266 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.61822/amcs-2025-0018","is_oa":true,"landing_page_url":"https://doi.org/10.61822/amcs-2025-0018","pdf_url":null,"source":{"id":"https://openalex.org/S117679522","display_name":"International Journal of Applied Mathematics and Computer Science","issn_l":"1641-876X","issn":["1641-876X","2083-8492"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320322","host_organization_name":"De Gruyter Open","host_organization_lineage":["https://openalex.org/P4310320322","https://openalex.org/P4310313990"],"host_organization_lineage_names":["De Gruyter Open","De Gruyter"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Applied Mathematics and Computer Science","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.6100000143051147}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2381411913","https://openalex.org/W2087331387","https://openalex.org/W4367000426","https://openalex.org/W4206903459","https://openalex.org/W2006060538","https://openalex.org/W4386047771","https://openalex.org/W2754816816","https://openalex.org/W2107708607","https://openalex.org/W4366280654","https://openalex.org/W3160167280"],"abstract_inverted_index":{"Recent":[0],"works":[1,28],"have":[2],"developed":[3],"model":[4,89],"complexity":[5],"based":[6,9],"and":[7,36,70,79,84,142,149,172],"algorithm":[8],"generalization":[10,54,115,188],"error":[11,55,116,189],"bounds":[12,56],"to":[13,38,52,93,163],"explain":[14],"how":[15],"stochastic":[16],"gradient":[17,73,100],"descent":[18],"(SGD)":[19],"methods":[20,162,180],"help":[21,164],"over-parameterized":[22],"models":[23,165],"generalize":[24,166],"better.":[25],"However,":[26],"previous":[27],"are":[29],"limited":[30],"by":[31],"their":[32],"scope":[33],"of":[34,65,121,161,186],"analysis":[35],"fail":[37],"provide":[39],"comprehensive":[40],"explanations.":[41],"In":[42],"this":[43],"paper,":[44],"we":[45,80,108,156],"propose":[46,157],"a":[47,63,105,110],"novel":[48],"Gaussian":[49],"approximation":[50],"framework":[51],"establish":[53,109],"for":[57,145],"the":[58,87,98,119,146,170,183,187],"\ud835\udcb0-SGD":[59,77,106],"family,":[60,107],"which":[61],"is":[62,102],"class":[64],"SGD":[66],"with":[67],"asymptotically":[68],"unbiased":[69],"uniformly":[71],"bounded":[72],"noise.":[74],"We":[75,176],"study":[76],"dynamics,":[78],"show":[81,177],"both":[82],"theoretically":[83],"numerically":[85],"that":[86,178],"limiting":[88],"parameter":[90,150],"distribution":[91],"tends":[92],"be":[94],"Gaussian,":[95],"even":[96],"when":[97],"original":[99],"noise":[101,174],"non-Gaussian.":[103],"For":[104],"desirable":[111],"iteration":[112],"number":[113],"independent":[114],"bound":[117],"at":[118],"order":[120],"\ud835\udcaa((1+log(pn))/n)":[122],"\\mathcal{O}\\left(":[123],"{\\left(":[124],"{1":[125],"+":[126],"\\sqrt":[127],"{\\log":[128],"\\left(":[129],"{p\\sqrt":[130],"n":[131,136,141],"}":[132,134,137],"\\right)}":[133],"\\right)/\\sqrt":[135],"\\right)":[138],",":[139],"where":[140],"p":[143],"stand":[144],"sample":[147],"size":[148],"dimension.":[151],"Based":[152],"on":[153],"our":[154],"analysis,":[155],"two":[158],"general":[159],"types":[160],"better,":[167],"termed":[168],"as":[169],"additive":[171],"multiplicative":[173],"insertions.":[175],"these":[179],"significantly":[181],"reduce":[182],"dominant":[184],"term":[185],"bound.":[190]},"counts_by_year":[],"updated_date":"2026-06-13T06:13:01.061226","created_date":"2025-07-01T00:00:00"}