{"id":"https://openalex.org/W7159575159","doi":"https://doi.org/10.48550/arxiv.2604.27987","title":"Dynamic Scaled Gradient Descent for Stable Fine-Tuning for Classifications","display_name":"Dynamic Scaled Gradient Descent for Stable Fine-Tuning for Classifications","publication_year":2026,"publication_date":"2026-04-30","ids":{"openalex":"https://openalex.org/W7159575159","doi":"https://doi.org/10.48550/arxiv.2604.27987"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.27987","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.27987","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":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.27987","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5134995991","display_name":"Nghia Bui","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bui, Nghia","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5134955810","display_name":"Lijing Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Lijing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.6398000121116638,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.6398000121116638,"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":0.12319999933242798,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.0738999992609024,"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/benchmark","display_name":"Benchmark (surveying)","score":0.7319999933242798},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.6974999904632568},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.6093000173568726},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.5055000185966492},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.49779999256134033},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.4047999978065491},{"id":"https://openalex.org/keywords/descent","display_name":"Descent (aeronautics)","score":0.3546000123023987}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7319999933242798},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.6974999904632568},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6254000067710876},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.6093000173568726},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.5055000185966492},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.49779999256134033},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4115000069141388},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.40529999136924744},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.4047999978065491},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35989999771118164},{"id":"https://openalex.org/C2776637919","wikidata":"https://www.wikidata.org/wiki/Q624380","display_name":"Descent (aeronautics)","level":2,"score":0.3546000123023987},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.34700000286102295},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.32019999623298645},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3021000027656555},{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.2791999876499176},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2678999900817871},{"id":"https://openalex.org/C115680565","wikidata":"https://www.wikidata.org/wiki/Q5977448","display_name":"Gradient method","level":2,"score":0.2669000029563904},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.2605000138282776},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.25769999623298645}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.27987","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.27987","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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.27987","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.27987","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":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Fine-tuning":[0],"pretrained":[1,10,116],"models":[2],"has":[3],"become":[4],"a":[5,28,62,89,106],"standard":[6],"approach":[7],"to":[8,12,37],"adapting":[9],"knowledge":[11],"improve":[13],"the":[14,32,49,73,82,128],"accuracy":[15,129],"on":[16,105],"new":[17],"sparse,":[18],"imbalance":[19],"datasets.":[20],"However,":[21],"issues":[22],"arise":[23],"when":[24],"optimization":[25],"falls":[26],"into":[27],"collapsed":[29],"state,":[30],"where":[31],"model":[33],"gets":[34],"stuck,":[35],"leading":[36],"degraded":[38],"performance":[39,124],"and":[40,97,114,126],"unstable":[41],"training.":[42],"One":[43],"possible":[44],"reason":[45],"for":[46],"this":[47,58],"is":[48],"cancellation":[50],"of":[51,84,108,130],"gradients":[52,74,83],"across":[53],"training":[54,77,102],"examples.":[55],"To":[56],"address":[57],"problem,":[59],"we":[60],"propose":[61],"novel":[63],"algorithm,":[64],"dynamic":[65,90],"scaled":[66],"gradient":[67],"descent":[68],"(\\mName),":[69],"that":[70,119],"directly":[71],"modifies":[72],"returned":[75],"by":[76],"examples,":[78],"specifically,":[79],"scaling":[80],"down":[81],"correctly":[85],"classified":[86],"examples":[87],"using":[88],"scaler.":[91],"This":[92],"strategy":[93],"offers":[94],"both":[95],"theoretical":[96],"empirical":[98],"advantages":[99],"in":[100],"improving":[101],"stability.":[103],"Experiments":[104],"variety":[107],"benchmark":[109],"datasets,":[110],"spanning":[111],"multiple":[112],"tasks":[113],"large":[115],"models,":[117],"demonstrate":[118],"our":[120],"method":[121],"consistently":[122],"reduces":[123],"variance":[125],"surpasses":[127],"existing":[131],"approaches.":[132]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-02T00:00:00"}