{"id":"https://openalex.org/W4385565434","doi":"https://doi.org/10.1145/3580305.3599501","title":"Sharpness-Aware Minimization Revisited: Weighted Sharpness as a Regularization Term","display_name":"Sharpness-Aware Minimization Revisited: Weighted Sharpness as a Regularization Term","publication_year":2023,"publication_date":"2023-08-04","ids":{"openalex":"https://openalex.org/W4385565434","doi":"https://doi.org/10.1145/3580305.3599501"},"language":"en","primary_location":{"id":"doi:10.1145/3580305.3599501","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3580305.3599501","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","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/A5079013709","display_name":"Yun Yue","orcid":"https://orcid.org/0000-0002-1430-7519"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Yun Yue","raw_affiliation_strings":["Ant Group, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Ant Group, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103172531","display_name":"Jiadi Jiang","orcid":"https://orcid.org/0000-0002-5998-0037"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiadi Jiang","raw_affiliation_strings":["Ant Group, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Ant Group, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027802232","display_name":"Zhiling Ye","orcid":"https://orcid.org/0009-0001-1229-5876"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhiling Ye","raw_affiliation_strings":["Ant Group, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Ant Group, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101800175","display_name":"Ning Gao","orcid":"https://orcid.org/0000-0002-4458-2132"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ning Gao","raw_affiliation_strings":["Ant Group, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Ant Group, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100617992","display_name":"Yongchao Liu","orcid":"https://orcid.org/0000-0003-3440-9675"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yongchao Liu","raw_affiliation_strings":["Ant Group, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Ant Group, Hangzhou, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101488120","display_name":"Ke Zhang","orcid":"https://orcid.org/0009-0008-6685-1293"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ke Zhang","raw_affiliation_strings":["Ant Group, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Ant Group, Beijing, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5079013709"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8643,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.75405294,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"3185","last_page":"3194"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998999834060669,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9995999932289124,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9990000128746033,"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/maxima-and-minima","display_name":"Maxima and minima","score":0.8078417181968689},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.7111878395080566},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6846281290054321},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6619512438774109},{"id":"https://openalex.org/keywords/minification","display_name":"Minification","score":0.6128096580505371},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.5753140449523926},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4839246869087219},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.44052496552467346},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.43962493538856506},{"id":"https://openalex.org/keywords/flatness","display_name":"Flatness (cosmology)","score":0.43633729219436646},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.42450541257858276},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.42038416862487793},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2707040309906006},{"id":"https://openalex.org/keywords/universe","display_name":"Universe","score":0.07452812790870667}],"concepts":[{"id":"https://openalex.org/C186633575","wikidata":"https://www.wikidata.org/wiki/Q845060","display_name":"Maxima and minima","level":2,"score":0.8078417181968689},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.7111878395080566},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6846281290054321},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6619512438774109},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.6128096580505371},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.5753140449523926},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4839246869087219},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.44052496552467346},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.43962493538856506},{"id":"https://openalex.org/C2778530986","wikidata":"https://www.wikidata.org/wiki/Q5457948","display_name":"Flatness (cosmology)","level":3,"score":0.43633729219436646},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.42450541257858276},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.42038416862487793},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2707040309906006},{"id":"https://openalex.org/C84999194","wikidata":"https://www.wikidata.org/wiki/Q1","display_name":"Universe","level":2,"score":0.07452812790870667},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C44870925","wikidata":"https://www.wikidata.org/wiki/Q37547","display_name":"Astrophysics","level":1,"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/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3580305.3599501","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3580305.3599501","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Partnerships for the goals","score":0.5199999809265137,"id":"https://metadata.un.org/sdg/17"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W607505555","https://openalex.org/W1988720110","https://openalex.org/W2029029543","https://openalex.org/W2117539524","https://openalex.org/W2194775991","https://openalex.org/W2560674852","https://openalex.org/W2747329762","https://openalex.org/W2912811302","https://openalex.org/W2964137095","https://openalex.org/W3207523779","https://openalex.org/W4238284510"],"related_works":["https://openalex.org/W2121922170","https://openalex.org/W4250124476","https://openalex.org/W4210838092","https://openalex.org/W4246857588","https://openalex.org/W2127982566","https://openalex.org/W2153731865","https://openalex.org/W1504381128","https://openalex.org/W2471196694","https://openalex.org/W1985711950","https://openalex.org/W2294590153"],"abstract_inverted_index":{"Deep":[0],"Neural":[1],"Networks":[2],"(DNNs)":[3],"generalization":[4,58],"is":[5,85,101],"known":[6],"to":[7,11,17,91],"be":[8],"closely":[9],"related":[10],"the":[12,18,36,61,92],"flatness":[13],"of":[14,20,38,63],"minima,":[15],"leading":[16],"development":[19],"Sharpness-Aware":[21],"Minimization":[22],"(SAM)":[23],"for":[24],"seeking":[25],"flatter":[26],"minima":[27],"and":[28,40,65,68,96],"better":[29],"generalization.":[30],"In":[31],"this":[32,104],"paper,":[33],"we":[34],"revisit":[35],"loss":[37],"SAM":[39,95],"propose":[41],"a":[42,52],"more":[43],"general":[44],"method,":[45],"called":[46],"WSAM,":[47],"by":[48],"incorporating":[49],"sharpness":[50],"as":[51],"regularization":[53],"term.":[54],"We":[55],"prove":[56],"its":[57,70,97],"bound":[59],"through":[60],"combination":[62],"PAC":[64],"Bayes-PAC":[66],"techniques,":[67],"evaluate":[69],"performance":[71],"on":[72],"various":[73],"public":[74],"datasets.":[75],"The":[76,99],"results":[77],"demonstrate":[78],"that":[79],"WSAM":[80],"achieves":[81],"improved":[82],"generalization,":[83],"or":[84],"at":[86,103],"least":[87],"highly":[88],"competitive,":[89],"compared":[90],"vanilla":[93],"optimizer,":[94],"variants.":[98],"code":[100],"available":[102],"link":[105],"https://github.com/intelligent-machine-learning/dlrover/tree/master/atorch/atorch/optimizers.":[106]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}