{"id":"https://openalex.org/W7163156491","doi":"https://doi.org/10.48550/arxiv.2606.02526","title":"Why Not Hyperparameter-Friendly Optimisation? A Monotonic Adaptive Norm Rescaling Approach For Long-Tailed Recognition","display_name":"Why Not Hyperparameter-Friendly Optimisation? A Monotonic Adaptive Norm Rescaling Approach For Long-Tailed Recognition","publication_year":2026,"publication_date":"2026-06-01","ids":{"openalex":"https://openalex.org/W7163156491","doi":"https://doi.org/10.48550/arxiv.2606.02526"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.02526","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.02526","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.2606.02526","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5137630129","display_name":"Shuo Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Shuo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137702368","display_name":"Chenqi Li","orcid":"https://orcid.org/0009-0006-4859-1681"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Chenqi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5137619394","display_name":"Tingting Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Tingting","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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.453000009059906,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.453000009059906,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.16279999911785126,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.10140000283718109,"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/monotonic-function","display_name":"Monotonic function","score":0.7642999887466431},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.6401000022888184},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5778999924659729},{"id":"https://openalex.org/keywords/norm","display_name":"Norm (philosophy)","score":0.5016000270843506},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38510000705718994}],"concepts":[{"id":"https://openalex.org/C72169020","wikidata":"https://www.wikidata.org/wiki/Q194404","display_name":"Monotonic function","level":2,"score":0.7642999887466431},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.6401000022888184},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6032999753952026},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5778999924659729},{"id":"https://openalex.org/C191795146","wikidata":"https://www.wikidata.org/wiki/Q3878446","display_name":"Norm (philosophy)","level":2,"score":0.5016000270843506},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.49129998683929443},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4246000051498413},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.38600000739097595},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38510000705718994},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.34459999203681946},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3093000054359436},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.27000001072883606},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.2630000114440918}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.02526","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.02526","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.2606.02526","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.02526","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":{"Long-tailed":[0],"recognition":[1,55,145],"poses":[2],"a":[3,21,33,73,85,122],"significant":[4],"challenge":[5],"for":[6,99,131],"deep":[7],"learning.":[8],"The":[9],"two-stage":[10],"decoupling":[11],"paradigm,":[12],"which":[13,45],"separates":[14],"representation":[15],"learning":[16],"from":[17],"classifier":[18,26],"retraining,":[19],"offers":[20],"promising":[22],"solution.":[23],"During":[24],"the":[25,38,97,111,117],"retraining":[27],"stage,":[28],"adaptive":[29],"norm":[30,79],"rescaling":[31,80],"is":[32,56,121],"popular":[34],"technique.":[35],"It":[36,102],"adjusts":[37],"per-class":[39,107],"weight":[40,108],"norms":[41,109],"via":[42],"parameter":[43,100],"regularization,":[44],"inevitably":[46],"introduces":[47],"hyperparameters.":[48],"However,":[49],"many":[50],"studies":[51],"report":[52],"that":[53,125,139],"long-tailed":[54,144],"sensitive":[57],"to":[58,77],"these":[59],"hyperparameters,":[60],"as":[61],"their":[62],"setup":[63],"significantly":[64,142],"impacts":[65],"performance.":[66,133],"In":[67],"this":[68],"paper,":[69],"we":[70,83],"first":[71],"provide":[72],"class-conditional":[74],"distribution":[75],"perspective":[76],"support":[78],"methods.":[81],"Furthermore,":[82],"propose":[84],"simple":[86],"but":[87],"effective":[88],"approach":[89],"called":[90],"Self-Adaptive":[91],"Monotonic":[92],"Normalization":[93],"(SAMN).":[94],"SAMN":[95,120],"avoids":[96],"need":[98],"regularization.":[101],"directly":[103],"enforces":[104],"monotonicity":[105],"on":[106,135],"using":[110],"Pool":[112],"Adjacent":[113],"Violators":[114],"Algorithm,":[115],"making":[116],"method":[118,141],"hyperparameter-friendly.":[119],"universal":[123],"strategy":[124],"integrates":[126],"seamlessly":[127],"with":[128],"other":[129],"methods":[130],"enhanced":[132],"Experiments":[134],"benchmark":[136],"datasets":[137],"demonstrate":[138],"our":[140],"boosts":[143],"performance,":[146],"often":[147],"achieving":[148],"state-of-the-art":[149],"results.":[150]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-03T00:00:00"}