{"id":"https://openalex.org/W7220722362","doi":"https://doi.org/10.48550/arxiv.2610.06421","title":"On the Comparison of Optimizers for Imbalanced Learning","display_name":"On the Comparison of Optimizers for Imbalanced Learning","publication_year":2026,"publication_date":"2026-10-05","ids":{"openalex":"https://openalex.org/W7220722362","doi":"https://doi.org/10.48550/arxiv.2610.06421"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.06421","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.06421","pdf_url":"https://arxiv.org/pdf/2610.06421","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2610.06421","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5049533142","display_name":"Cl\u00e9ment Lezane","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lezane, Cl{\u00e9}ment","raw_affiliation_strings":["ANITI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ANITI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5157699539","display_name":"Fran{\\c c}ois Bachoc","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bachoc, Fran{\\c c}ois","raw_affiliation_strings":["LPP"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LPP","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5157676922","display_name":"J{\u00e9}r{\u00f4}me Bolte","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bolte, J{\u00e9}r{\u00f4}me","raw_affiliation_strings":["ANITI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ANITI","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025032659","display_name":"Jean\u2013Michel Loubes","orcid":"https://orcid.org/0000-0002-1252-2960","observed_orcids":["https://orcid.org/0000-0002-1252-2960"]},"institutions":[{"id":"https://openalex.org/I4405263062","display_name":"REGALIA: R\u00e9gulation de l'Intelligence Artificielle","ror":"https://ror.org/01zthd343","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1326498283","https://openalex.org/I4405263062"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Loubes, Jean-Michel","raw_affiliation_strings":["IMT,REGALIA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IMT,REGALIA","institution_ids":["https://openalex.org/I4405263062"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.4641000032424927,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.4641000032424927,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.46239998936653137,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.049800001084804535,"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/imbalanced-learning","display_name":"imbalanced learning","score":0.9610000252723694},{"id":"https://openalex.org/keywords/class-imbalance","display_name":"class imbalance","score":0.6200000047683716},{"id":"https://openalex.org/keywords/optimization-algorithm-comparison","display_name":"optimizer comparison","score":0.597000002861023},{"id":"https://openalex.org/keywords/continuous-time-dynamics","display_name":"continuous-time dynamics","score":0.6909999847412109},{"id":"https://openalex.org/keywords/adamw","display_name":"AdamW","score":0.8069999814033508},{"id":"https://openalex.org/keywords/muon-optimizer","display_name":"Muon optimizer","score":0.906000018119812},{"id":"https://openalex.org/keywords/sgd","display_name":"SGD","score":0.4359999895095825},{"id":"https://openalex.org/keywords/tabular-data","display_name":"tabular data","score":0.609000027179718},{"id":"https://openalex.org/keywords/language-models","display_name":"language models","score":0.4180000126361847},{"id":"https://openalex.org/keywords/image-classification","display_name":"image classification","score":0.8029999732971191}],"concepts":[{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.6122000217437744},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5442000031471252},{"id":"https://openalex.org/C129782007","wikidata":"https://www.wikidata.org/wiki/Q162886","display_name":"Euclidean geometry","level":2,"score":0.5257999897003174},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.51910001039505},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.5112000107765198},{"id":"https://openalex.org/C2776637919","wikidata":"https://www.wikidata.org/wiki/Q624380","display_name":"Descent (aeronautics)","level":2,"score":0.5112000107765198},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.4875999987125397},{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.460999995470047},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4253999888896942},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.40880000591278076},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.4009000062942505},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.38440001010894775},{"id":"https://openalex.org/C120174047","wikidata":"https://www.wikidata.org/wiki/Q847073","display_name":"Euclidean distance","level":2,"score":0.3741999864578247},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3725000023841858},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3720000088214874},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3653999865055084},{"id":"https://openalex.org/C180205008","wikidata":"https://www.wikidata.org/wiki/Q159190","display_name":"Amplitude","level":2,"score":0.3598000109195709},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34380000829696655},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.3190000057220459},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.28369998931884766},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.26190000772476196}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:arXiv.org:2610.06421","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.06421","pdf_url":"https://arxiv.org/pdf/2610.06421","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:HAL:hal-05775266v1","doi":null,"is_oa":true,"landing_page_url":"https://hal.science/hal-05775266","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4405252976","host_organization_name":"Centre pour la Communication Scientifique Directe","host_organization_lineage":["https://openalex.org/I4405252976"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2026","raw_type":"info:eu-repo/semantics/preprint"},{"id":"doi:10.48550/arxiv.2610.06421","doi":"https://doi.org/10.48550/arxiv.2610.06421","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.06421","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2610.06421","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.06421","pdf_url":"https://arxiv.org/pdf/2610.06421","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.5676000118255615,"id":"https://metadata.un.org/sdg/10"}],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7220722362.pdf","grobid_xml":"https://content.openalex.org/works/W7220722362.grobid-xml"},"referenced_works_count":12,"referenced_works":["https://openalex.org/W1486089539","https://openalex.org/W2029213856","https://openalex.org/W2048176942","https://openalex.org/W2975035192","https://openalex.org/W4322718191","https://openalex.org/W4414803876","https://openalex.org/W4414898866","https://openalex.org/W4415798379","https://openalex.org/W7101885942","https://openalex.org/W7160984813","https://openalex.org/W7162435015","https://openalex.org/W7204199371"],"related_works":["https://openalex.org/W4283816583","https://openalex.org/W4415798379","https://openalex.org/W2897069058","https://openalex.org/W3111007040","https://openalex.org/W7101885942","https://openalex.org/W4416954965","https://openalex.org/W6904944166","https://openalex.org/W4315641811","https://openalex.org/W3196196682","https://openalex.org/W6962722384"],"abstract_inverted_index":{"Data":[0],"imbalance":[1,41],"is":[2,42],"pervasive":[3],"in":[4,15,25,32],"machine":[5],"learning,":[6],"from":[7],"rare":[8],"words":[9],"and":[10,61,89,110,121,131],"anomalies":[11],"to":[12,28,49,95],"underrepresented":[13],"patterns":[14],"heterogeneous":[16],"or":[17],"cross-tabulated":[18],"data.":[19],"We":[20,35,82],"study":[21],"idealized":[22],"optimizers":[23],"geometries":[24],"continuous":[26],"time":[27,93],"model":[29],"small-step":[30],"training":[31,52],"deep":[33],"learning.":[34],"assume":[36],"that":[37],"the":[38,44,50,55,59,78,92],"source":[39],"of":[40,58,77,86],"unobserved:":[43],"optimizer":[45],"has":[46],"only":[47],"access":[48],"aggregate":[51],"loss":[53],"ignoring":[54],"exact":[56],"contributions":[57],"majority":[60,72],"minority":[62,80,105],"groups.":[63],"In":[64],"this":[65,87],"setting,":[66],"we":[67],"characterize":[68],"a":[69,101],"region":[70],"where":[71],"losses":[73],"are":[74],"optimized":[75],"regardless":[76],"admissible":[79],"structure.":[81],"derive":[83],"explicit":[84],"equations":[85],"zone":[88],"bounds":[90,99],"on":[91,104],"needed":[94],"leave":[96],"it.":[97],"These":[98],"exhibit":[100],"milder":[102],"dependence":[103],"amplitude":[106],"for":[107,114],"sign,":[108],"spectral,":[109],"Newton":[111],"descent":[112],"than":[113],"Euclidean":[115],"gradient":[116],"descent.":[117],"Experiments":[118],"with":[119],"AdamW":[120],"Muon":[122],"suggest":[123],"similar":[124],"advantages":[125],"over":[126],"SGD":[127],"across":[128],"language,":[129],"tabular,":[130],"image":[132],"tasks.":[133]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-10-07T00:00:00"}