{"id":"https://openalex.org/W4411726037","doi":"https://doi.org/10.1109/tpami.2025.3581310","title":"Systematic Investigation of Sparse Perturbed Sharpness-Aware Minimization Optimizer","display_name":"Systematic Investigation of Sparse Perturbed Sharpness-Aware Minimization Optimizer","publication_year":2025,"publication_date":"2025-06-27","ids":{"openalex":"https://openalex.org/W4411726037","doi":"https://doi.org/10.1109/tpami.2025.3581310","pmid":"https://pubmed.ncbi.nlm.nih.gov/40577305"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2025.3581310","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3581310","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5008806319","display_name":"\u670b\u5b50 \u9375\u5f25","orcid":"https://orcid.org/0009-0004-2911-4965"},"institutions":[{"id":"https://openalex.org/I1327237609","display_name":"Ministry of Education of the People's Republic of China","ror":"https://ror.org/01mv9t934","country_code":"CN","type":"government","lineage":["https://openalex.org/I1327237609","https://openalex.org/I4210127390"]},{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Peng Mi","raw_affiliation_strings":["Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China","Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, P.R. China"],"raw_orcid":"https://orcid.org/0009-0004-2911-4965","affiliations":[{"raw_affiliation_string":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]},{"raw_affiliation_string":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, P.R. China","institution_ids":["https://openalex.org/I1327237609","https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042802004","display_name":"Li Shen","orcid":"https://orcid.org/0000-0001-5659-3464"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Shen","raw_affiliation_strings":["School of Cyber Science and Technology, Shenzhen Campus of Sun Yat-sen University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0001-5659-3464","affiliations":[{"raw_affiliation_string":"School of Cyber Science and Technology, Shenzhen Campus of Sun Yat-sen University, Shenzhen, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052555143","display_name":"Tianhe Ren","orcid":"https://orcid.org/0000-0003-3121-4020"},"institutions":[{"id":"https://openalex.org/I1327237609","display_name":"Ministry of Education of the People's Republic of China","ror":"https://ror.org/01mv9t934","country_code":"CN","type":"government","lineage":["https://openalex.org/I1327237609","https://openalex.org/I4210127390"]},{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianhe Ren","raw_affiliation_strings":["Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China","Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]},{"raw_affiliation_string":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, P.R. China","institution_ids":["https://openalex.org/I1327237609","https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yiyi Zhou","orcid":"https://orcid.org/0000-0002-5110-4526"},"institutions":[{"id":"https://openalex.org/I1327237609","display_name":"Ministry of Education of the People's Republic of China","ror":"https://ror.org/01mv9t934","country_code":"CN","type":"government","lineage":["https://openalex.org/I1327237609","https://openalex.org/I4210127390"]},{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiyi Zhou","raw_affiliation_strings":["Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China","Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, P.R. China"],"raw_orcid":"https://orcid.org/0000-0002-5110-4526","affiliations":[{"raw_affiliation_string":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]},{"raw_affiliation_string":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, P.R. China","institution_ids":["https://openalex.org/I1327237609","https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102446549","display_name":"Tianshuo Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I1327237609","display_name":"Ministry of Education of the People's Republic of China","ror":"https://ror.org/01mv9t934","country_code":"CN","type":"government","lineage":["https://openalex.org/I1327237609","https://openalex.org/I4210127390"]},{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianshuo Xu","raw_affiliation_strings":["Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China","Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, P.R. China"],"raw_orcid":"https://orcid.org/0009-0006-2142-4664","affiliations":[{"raw_affiliation_string":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]},{"raw_affiliation_string":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, P.R. China","institution_ids":["https://openalex.org/I1327237609","https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059926864","display_name":"Xiaoshuai Sun","orcid":"https://orcid.org/0000-0003-3912-9306"},"institutions":[{"id":"https://openalex.org/I1327237609","display_name":"Ministry of Education of the People's Republic of China","ror":"https://ror.org/01mv9t934","country_code":"CN","type":"government","lineage":["https://openalex.org/I1327237609","https://openalex.org/I4210127390"]},{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoshuai Sun","raw_affiliation_strings":["Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China","Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, P.R. China"],"raw_orcid":"https://orcid.org/0000-0003-3912-9306","affiliations":[{"raw_affiliation_string":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]},{"raw_affiliation_string":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, P.R. China","institution_ids":["https://openalex.org/I1327237609","https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065250332","display_name":"Tongliang Liu","orcid":"https://orcid.org/0000-0002-9640-6472"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Tongliang Liu","raw_affiliation_strings":["The University of Sydney, Camperdown, NSW, Australia","University of Sydney, Australia"],"raw_orcid":"https://orcid.org/0000-0002-9640-6472","affiliations":[{"raw_affiliation_string":"The University of Sydney, Camperdown, NSW, Australia","institution_ids":["https://openalex.org/I129604602"]},{"raw_affiliation_string":"University of Sydney, Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016080094","display_name":"Rongrong Ji","orcid":"https://orcid.org/0000-0001-9163-2932"},"institutions":[{"id":"https://openalex.org/I1327237609","display_name":"Ministry of Education of the People's Republic of China","ror":"https://ror.org/01mv9t934","country_code":"CN","type":"government","lineage":["https://openalex.org/I1327237609","https://openalex.org/I4210127390"]},{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rongrong Ji","raw_affiliation_strings":["Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China","Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, P.R. China"],"raw_orcid":"https://orcid.org/0000-0001-9163-2932","affiliations":[{"raw_affiliation_string":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]},{"raw_affiliation_string":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, P.R. China","institution_ids":["https://openalex.org/I1327237609","https://openalex.org/I191208505"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046877006","display_name":"Dacheng Tao","orcid":null},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]},{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["AU","SG"],"is_corresponding":false,"raw_author_name":"Dacheng Tao","raw_affiliation_strings":["College of Computing and Data Science, Nanyang Technological University, Singapore","University of Sydney, Australia"],"raw_orcid":"https://orcid.org/0000-0001-7225-5449","affiliations":[{"raw_affiliation_string":"College of Computing and Data Science, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"University of Sydney, Australia","institution_ids":["https://openalex.org/I129604602"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5008806319"],"corresponding_institution_ids":["https://openalex.org/I1327237609","https://openalex.org/I191208505"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.14995364,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"47","issue":"10","first_page":"8538","last_page":"8549"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13049","display_name":"Surface Roughness and Optical Measurements","score":0.9379000067710876,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"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/T13049","display_name":"Surface Roughness and Optical Measurements","score":0.9379000067710876,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/minification","display_name":"Minification","score":0.7354617118835449},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6223519444465637},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5556648373603821},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3965112566947937},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38836973905563354},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3795032501220703}],"concepts":[{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.7354617118835449},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6223519444465637},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5556648373603821},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3965112566947937},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38836973905563354},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3795032501220703},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2025.3581310","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3581310","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:40577305","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40577305","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W114517082","https://openalex.org/W153185079","https://openalex.org/W2029029543","https://openalex.org/W2084840427","https://openalex.org/W2097317843","https://openalex.org/W2108598243","https://openalex.org/W2130984546","https://openalex.org/W2183341477","https://openalex.org/W2194775991","https://openalex.org/W2560647685","https://openalex.org/W2963140066","https://openalex.org/W2963433607","https://openalex.org/W2963470657","https://openalex.org/W2964137095","https://openalex.org/W2965862774","https://openalex.org/W2992308087","https://openalex.org/W3138516171","https://openalex.org/W3207523779","https://openalex.org/W4385245566","https://openalex.org/W4402716202"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Deep":[0],"neural":[1],"networks":[2],"often":[3],"suffer":[4],"from":[5],"poor":[6],"generalization":[7],"due":[8],"to":[9,39,155,177],"complex":[10],"and":[11,52,78,103,118,126,158,169,183],"non-convex":[12],"loss":[13,25,34,161],"landscapes.":[14],"Sharpness-Aware":[15],"Minimization":[16],"(SAM)":[17],"is":[18,50,175,186],"a":[19,37,87,192],"popular":[20],"solution":[21],"that":[22,82,136,172],"smooths":[23],"the":[24,29,40,58,92,110,141,153,160,184],"landscape":[26,162],"by":[27,86],"minimizing":[28],"maximized":[30],"change":[31],"of":[32,45,60,112,129,181,194],"training":[33,80,157],"when":[35],"adding":[36],"perturbation":[38,44,85,193],"weight.":[41],"However,":[42],"indiscriminate":[43],"SAM":[46,74,151,178],"on":[47,100,167],"all":[48],"parameters":[49],"suboptimal":[51],"results":[53,166],"in":[54,179],"excessive":[55],"computation,":[56],"double":[57],"overhead":[59],"common":[61],"optimizers":[62],"like":[63],"Stochastic":[64],"Gradient":[65],"Descent":[66],"(SGD).":[67],"In":[68],"this":[69],"paper,":[70],"we":[71,95],"propose":[72],"Sparse":[73,150],"(SSAM),":[75],"an":[76],"efficient":[77],"effective":[79],"scheme":[81],"achieves":[83],"sparse":[84,93,105,131],"binary":[88],"mask.":[89],"To":[90],"obtain":[91],"mask,":[94],"provide":[96],"two":[97],"solutions":[98],"based":[99],"Fisher":[101],"information":[102],"dynamic":[104],"training,":[106],"respectively.":[107],"We":[108,133],"investigate":[109],"impact":[111],"different":[113],"masks,":[114],"including":[115],"unstructured,":[116],"structured,":[117],"$N$N:$M$M":[119],"structured":[120],"patterns,":[121],"as":[122,124,144],"well":[123],"explicit":[125],"implicit":[127],"forms":[128],"implementing":[130],"perturbation.":[132],"theoretically":[134],"prove":[135],"SSAM":[137],"can":[138],"converge":[139],"at":[140],"same":[142],"rate":[143],"SAM,":[145],"i.e.,":[146],"$O(\\log":[147],"T/\\sqrt{T})$O(logT/T)":[148],".":[149],"has":[152],"potential":[154],"accelerate":[156],"smooth":[159],"effectively.":[163],"Extensive":[164],"experimental":[165],"CIFAR":[168],"ImageNet-1K":[170],"confirm":[171],"our":[173],"method":[174],"superior":[176],"terms":[180],"efficiency,":[182],"performance":[185],"preserved":[187],"or":[188],"even":[189],"improved":[190],"with":[191],"merely":[195],"50%":[196],"sparsity.":[197]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
