{"id":"https://openalex.org/W4289713078","doi":"https://doi.org/10.1109/isit50566.2022.9834839","title":"On how to avoid exacerbating spurious correlations when models are overparameterized","display_name":"On how to avoid exacerbating spurious correlations when models are overparameterized","publication_year":2022,"publication_date":"2022-06-26","ids":{"openalex":"https://openalex.org/W4289713078","doi":"https://doi.org/10.1109/isit50566.2022.9834839"},"language":"en","primary_location":{"id":"doi:10.1109/isit50566.2022.9834839","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isit50566.2022.9834839","pdf_url":null,"source":{"id":"https://openalex.org/S4363604560","display_name":"2022 IEEE International Symposium on Information Theory (ISIT)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Symposium on Information Theory (ISIT)","raw_type":"proceedings-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/A5090352249","display_name":"Tina Behnia","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Tina Behnia","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100360159","display_name":"Ke Wang","orcid":"https://orcid.org/0000-0003-4501-5102"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ke Wang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5024812488","display_name":"Christos Thrampoulidis","orcid":"https://orcid.org/0000-0001-9053-9365"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Christos Thrampoulidis","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5090352249"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1049,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.28015688,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"121","last_page":"126"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9977999925613403,"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":0.9977999925613403,"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":0.9972000122070312,"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/T10136","display_name":"Statistical Methods and Inference","score":0.9950000047683716,"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/spurious-relationship","display_name":"Spurious relationship","score":0.9126437902450562},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6254845857620239},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.6093475818634033},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6085433959960938},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.5419763326644897},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.5385333895683289},{"id":"https://openalex.org/keywords/population","display_name":"Population","score":0.510008692741394},{"id":"https://openalex.org/keywords/parametric-model","display_name":"Parametric model","score":0.4885035753250122},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.4817647933959961},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.467142790555954},{"id":"https://openalex.org/keywords/cross-entropy","display_name":"Cross entropy","score":0.4135856330394745},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4015377163887024},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40028202533721924},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33253538608551025},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3267768621444702},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3137841522693634},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.2931744158267975},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.15830200910568237},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.15750816464424133}],"concepts":[{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.9126437902450562},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6254845857620239},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.6093475818634033},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6085433959960938},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.5419763326644897},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.5385333895683289},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.510008692741394},{"id":"https://openalex.org/C24574437","wikidata":"https://www.wikidata.org/wiki/Q7135228","display_name":"Parametric model","level":3,"score":0.4885035753250122},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.4817647933959961},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.467142790555954},{"id":"https://openalex.org/C167981619","wikidata":"https://www.wikidata.org/wiki/Q1685498","display_name":"Cross entropy","level":3,"score":0.4135856330394745},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4015377163887024},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40028202533721924},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33253538608551025},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3267768621444702},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3137841522693634},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2931744158267975},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.15830200910568237},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.15750816464424133},{"id":"https://openalex.org/C149923435","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demography","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/isit50566.2022.9834839","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isit50566.2022.9834839","pdf_url":null,"source":{"id":"https://openalex.org/S4363604560","display_name":"2022 IEEE International Symposium on Information Theory (ISIT)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Symposium on Information Theory (ISIT)","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.kaust.edu.sa:10754/679606","is_oa":false,"landing_page_url":"http://hdl.handle.net/10754/679606","pdf_url":null,"source":{"id":"https://openalex.org/S4306401596","display_name":"King Abdullah University of Science and Technology Repository (King Abdullah University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I71920554","host_organization_name":"King Abdullah University of Science and Technology","host_organization_lineage":["https://openalex.org/I71920554"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5099999904632568,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":60,"referenced_works":["https://openalex.org/W835905657","https://openalex.org/W2566079294","https://openalex.org/W2790253170","https://openalex.org/W2921393178","https://openalex.org/W2963017107","https://openalex.org/W2963518130","https://openalex.org/W2967536008","https://openalex.org/W2970941190","https://openalex.org/W2984133899","https://openalex.org/W2991497298","https://openalex.org/W2997580736","https://openalex.org/W3004510491","https://openalex.org/W3018252856","https://openalex.org/W3020361330","https://openalex.org/W3021336872","https://openalex.org/W3105792944","https://openalex.org/W3122855191","https://openalex.org/W3131431103","https://openalex.org/W3173576323","https://openalex.org/W3213131041","https://openalex.org/W3213495149","https://openalex.org/W4226154270","https://openalex.org/W4287164429","https://openalex.org/W4287285260","https://openalex.org/W4287777768","https://openalex.org/W4287867244","https://openalex.org/W4287998573","https://openalex.org/W4288287305","https://openalex.org/W4288413101","https://openalex.org/W4295132142","https://openalex.org/W4297823929","https://openalex.org/W4299785371","https://openalex.org/W6623408330","https://openalex.org/W6637422517","https://openalex.org/W6745276634","https://openalex.org/W6748742374","https://openalex.org/W6760201928","https://openalex.org/W6760498417","https://openalex.org/W6764733053","https://openalex.org/W6765285020","https://openalex.org/W6767329639","https://openalex.org/W6769472860","https://openalex.org/W6771252938","https://openalex.org/W6771271773","https://openalex.org/W6772178927","https://openalex.org/W6773834485","https://openalex.org/W6773981018","https://openalex.org/W6776071938","https://openalex.org/W6776699476","https://openalex.org/W6777730395","https://openalex.org/W6779356556","https://openalex.org/W6780793664","https://openalex.org/W6790678048","https://openalex.org/W6791656692","https://openalex.org/W6793913008","https://openalex.org/W6794431197","https://openalex.org/W6796884226","https://openalex.org/W6797321547","https://openalex.org/W6803675131","https://openalex.org/W6810617761"],"related_works":["https://openalex.org/W3043437576","https://openalex.org/W4287722278","https://openalex.org/W3092041776","https://openalex.org/W3011996705","https://openalex.org/W3099765033","https://openalex.org/W2989932438","https://openalex.org/W3175189414","https://openalex.org/W4210794429","https://openalex.org/W4226084557","https://openalex.org/W4289713078"],"abstract_inverted_index":{"Overparameterized":[0],"learning":[1],"architectures":[2],"fail":[3,119],"to":[4,122],"generalize":[5],"well":[6],"in":[7,29],"the":[8,35,44,67,74,86,105,112,116],"presence":[9],"of":[10,34,51,76,141],"data":[11],"imbalance":[12],"even":[13,98,138],"when":[14,83,99],"combined":[15],"with":[16,43],"traditional":[17],"techniques":[18],"for":[19,128],"mitigating":[20],"imbalances.":[21],"This":[22],"paper":[23],"focuses":[24],"on":[25,66,73],"imbalanced":[26],"classification":[27],"datasets,":[28],"which":[30],"a":[31,48,56,91],"small":[32],"subset":[33],"population\u2014a":[36],"minority\u2014may":[37],"contain":[38],"features":[39,101],"that":[40,70,93],"correlate":[41],"spuriously":[42],"class":[45],"label.":[46],"For":[47],"parametric":[49],"family":[50],"cross-entropy":[52],"loss":[53],"modifications":[54],"and":[55,115],"representative":[57],"Gaussian":[58],"mixture":[59],"model,":[60],"we":[61,80],"derive":[62],"non-asymptotic":[63],"generalization":[64],"bounds":[65,126],"worst-group":[68],"error":[69],"shed":[71],"light":[72],"role":[75],"different":[77],"hyper-parameters.":[78],"Specifically,":[79],"prove":[81],"that,":[82],"appropriately":[84],"tuned,":[85],"recently":[87],"proposed":[88],"VS-loss":[89],"learns":[90],"model":[92],"is":[94],"fair":[95],"towards":[96],"minorities":[97],"spurious":[100],"are":[102,133],"strong.":[103],"On":[104],"other":[106],"hand,":[107],"alternative":[108],"heuristics,":[109],"such":[110],"as":[111],"weighted":[113],"CE":[114],"LA-loss,":[117],"can":[118],"dramatically.":[120],"Compared":[121],"previous":[123],"works,":[124],"our":[125],"hold":[127],"more":[129],"general":[130],"models,":[131],"they":[132,136],"non-asymptotic,":[134],"and,":[135],"apply":[137],"at":[139],"scenarios":[140],"extreme":[142],"imbalance.":[143]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-14T06:41:57.775601","created_date":"2025-10-10T00:00:00"}