{"id":"https://openalex.org/W7131413787","doi":"https://doi.org/10.1109/icdm65498.2025.00103","title":"Sharpness-Aware Optimization Through Variance Suppression on Deep AUC Maximization","display_name":"Sharpness-Aware Optimization Through Variance Suppression on Deep AUC Maximization","publication_year":2025,"publication_date":"2025-11-12","ids":{"openalex":"https://openalex.org/W7131413787","doi":"https://doi.org/10.1109/icdm65498.2025.00103"},"language":null,"primary_location":{"id":"doi:10.1109/icdm65498.2025.00103","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdm65498.2025.00103","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Data Mining (ICDM)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5061814617","display_name":"Xinwen Zhang","orcid":"https://orcid.org/0009-0002-1981-7523"},"institutions":[{"id":"https://openalex.org/I84392919","display_name":"Temple University","ror":"https://ror.org/00kx1jb78","country_code":"US","type":"education","lineage":["https://openalex.org/I84392919"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xinwen Zhang","raw_affiliation_strings":["Temple University,Department of Computer and Information Sciences,Philadelphia,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Temple University,Department of Computer and Information Sciences,Philadelphia,USA","institution_ids":["https://openalex.org/I84392919"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102798905","display_name":"Hongchang Gao","orcid":null},"institutions":[{"id":"https://openalex.org/I84392919","display_name":"Temple University","ror":"https://ror.org/00kx1jb78","country_code":"US","type":"education","lineage":["https://openalex.org/I84392919"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hongchang Gao","raw_affiliation_strings":["Temple University,Department of Computer and Information Sciences,Philadelphia,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Temple University,Department of Computer and Information Sciences,Philadelphia,USA","institution_ids":["https://openalex.org/I84392919"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I84392919"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.79079976,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"953","last_page":"962"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.08219999819993973,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.08219999819993973,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.061500001698732376,"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":0.05180000141263008,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/minimax","display_name":"Minimax","score":0.8219000101089478},{"id":"https://openalex.org/keywords/maximization","display_name":"Maximization","score":0.8029000163078308},{"id":"https://openalex.org/keywords/minification","display_name":"Minification","score":0.7461000084877014},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.6036999821662903},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5745999813079834},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.5092999935150146}],"concepts":[{"id":"https://openalex.org/C149728462","wikidata":"https://www.wikidata.org/wiki/Q751319","display_name":"Minimax","level":2,"score":0.8219000101089478},{"id":"https://openalex.org/C2776330181","wikidata":"https://www.wikidata.org/wiki/Q18358244","display_name":"Maximization","level":2,"score":0.8029000163078308},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.7461000084877014},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6036999821662903},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5938000082969666},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5745999813079834},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.5092999935150146},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4909999966621399},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4706999957561493},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4472000002861023},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.421099990606308},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.39149999618530273},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.38659998774528503},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.3840000033378601},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3449999988079071},{"id":"https://openalex.org/C2987595161","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Optimization algorithm","level":2,"score":0.3167000114917755},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2874000072479248},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2687999904155731}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icdm65498.2025.00103","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdm65498.2025.00103","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Data Mining (ICDM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W2157825442","https://openalex.org/W2194775991","https://openalex.org/W2552194003","https://openalex.org/W2912811302","https://openalex.org/W2963446712","https://openalex.org/W3121732873","https://openalex.org/W3138582970","https://openalex.org/W3166792421","https://openalex.org/W3196927126","https://openalex.org/W3207523779","https://openalex.org/W4312391126","https://openalex.org/W4313591702"],"related_works":[],"abstract_inverted_index":{"Sharpness-aware":[0,72],"minimization":[1,49],"(SAM)":[2],"is":[3],"widely":[4],"rec-ognized":[5],"for":[6,75,100,110],"its":[7],"ability":[8],"to":[9,27,56,94],"improve":[10],"the":[11,19,29,47,57,91,112,117,121],"generalization":[12],"of":[13,85,103,123],"deep":[14,76],"neural":[15],"networks":[16],"by":[17,33,69],"transforming":[18],"optimization":[20],"problem":[21],"into":[22],"a":[23,38,65,81],"minimax":[24,58],"problem,":[25,115],"aiming":[26],"minimize":[28],"maximum":[30],"loss":[31],"caused":[32],"adversarial":[34],"parameter":[35],"perturbations":[36],"within":[37],"neighborhood.":[39],"However,":[40],"existing":[41],"work":[42,93],"almost":[43],"exclusively":[44],"focuses":[45],"on":[46],"original":[48],"optimization,":[50],"with":[51],"very":[52],"little":[53],"attention":[54],"paid":[55],"optimization.":[59],"In":[60],"this":[61,86,101],"paper,":[62],"we":[63,106],"introduce":[64],"novel":[66],"algorithm,":[67,87],"VaSSO-SGDAM,":[68],"leveraging":[70],"Variance-Suppressed":[71],"Optimization":[73],"(VaSSO)":[74],"AUC":[77,113],"maximization.":[78],"We":[79],"provide":[80],"theoretical":[82,98],"convergence":[83],"analysis":[84],"marking":[88],"it":[89],"as":[90],"first":[92],"achieve":[95],"such":[96],"significant":[97],"outcomes":[99],"kind":[102],"problem.":[104],"Lastly,":[105],"implement":[107],"our":[108,124],"method":[109],"optimizing":[111],"maximization":[114],"and":[116],"experimental":[118],"findings":[119],"validate":[120],"efficacy":[122],"approach.":[125]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-02-26T00:00:00"}