{"id":"https://openalex.org/W4389366372","doi":"https://doi.org/10.1145/3628797.3629009","title":"Applying Adaptive Sharpness-Aware Minimization to Improve Out-of-distribution Generalization","display_name":"Applying Adaptive Sharpness-Aware Minimization to Improve Out-of-distribution Generalization","publication_year":2023,"publication_date":"2023-12-06","ids":{"openalex":"https://openalex.org/W4389366372","doi":"https://doi.org/10.1145/3628797.3629009"},"language":"en","primary_location":{"id":"doi:10.1145/3628797.3629009","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3628797.3629009","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th International Symposium on Information and Communication Technology","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/A5091095351","display_name":"Hoang-Chau Luong","orcid":"https://orcid.org/0000-0003-2306-072X"},"institutions":[{"id":"https://openalex.org/I23582244","display_name":"Ho Chi Minh City University of Science","ror":"https://ror.org/05jfbgm49","country_code":"VN","type":"education","lineage":["https://openalex.org/I123565023","https://openalex.org/I23582244"]}],"countries":["VN"],"is_corresponding":true,"raw_author_name":"Hoang-Chau Luong","raw_affiliation_strings":["University of Science, HCMVNU, Viet Nam"],"affiliations":[{"raw_affiliation_string":"University of Science, HCMVNU, Viet Nam","institution_ids":["https://openalex.org/I23582244"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053495766","display_name":"Minh\u2013Triet Tran","orcid":"https://orcid.org/0000-0003-3046-3041"},"institutions":[{"id":"https://openalex.org/I23582244","display_name":"Ho Chi Minh City University of Science","ror":"https://ror.org/05jfbgm49","country_code":"VN","type":"education","lineage":["https://openalex.org/I123565023","https://openalex.org/I23582244"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Minh-Triet Tran","raw_affiliation_strings":["University of Science, HCMVNU, Viet Nam"],"affiliations":[{"raw_affiliation_string":"University of Science, HCMVNU, Viet Nam","institution_ids":["https://openalex.org/I23582244"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5091095351"],"corresponding_institution_ids":["https://openalex.org/I23582244"],"apc_list":null,"apc_paid":null,"fwci":0.174,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.58910968,"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":"450","last_page":"455"},"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":0.9995999932289124,"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"}},"topics":[{"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9937000274658203,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9883000254631042,"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/robustness","display_name":"Robustness (evolution)","score":0.7962361574172974},{"id":"https://openalex.org/keywords/maxima-and-minima","display_name":"Maxima and minima","score":0.7503207921981812},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.7336456775665283},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6411639451980591},{"id":"https://openalex.org/keywords/minification","display_name":"Minification","score":0.5802589058876038},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4948579668998718},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.47356995940208435},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.44801729917526245},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.4405294358730316},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3210890293121338},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2447594404220581}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7962361574172974},{"id":"https://openalex.org/C186633575","wikidata":"https://www.wikidata.org/wiki/Q845060","display_name":"Maxima and minima","level":2,"score":0.7503207921981812},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.7336456775665283},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6411639451980591},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.5802589058876038},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4948579668998718},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.47356995940208435},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44801729917526245},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.4405294358730316},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3210890293121338},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2447594404220581},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3628797.3629009","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3628797.3629009","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th International Symposium on Information and Communication Technology","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W2031342017","https://openalex.org/W2952735550","https://openalex.org/W2958360136","https://openalex.org/W2963043696","https://openalex.org/W2995750307","https://openalex.org/W3033161486","https://openalex.org/W3044971416","https://openalex.org/W3113148327","https://openalex.org/W3168441138","https://openalex.org/W3196660344","https://openalex.org/W3212348395","https://openalex.org/W4289639938","https://openalex.org/W4309793942","https://openalex.org/W4312391126","https://openalex.org/W4312908248","https://openalex.org/W4386066238","https://openalex.org/W6796913975"],"related_works":["https://openalex.org/W2375684291","https://openalex.org/W2354676191","https://openalex.org/W3188646203","https://openalex.org/W2121922170","https://openalex.org/W4210838092","https://openalex.org/W2127982566","https://openalex.org/W2153731865","https://openalex.org/W1504381128","https://openalex.org/W2471196694","https://openalex.org/W1985711950"],"abstract_inverted_index":{"Out-of-distribution":[0],"(OoD)":[1],"generalization":[2,78,96,196],"in":[3,24,97,110,117,152,177],"machine":[4],"learning":[5],"occurs":[6],"when":[7,42,198],"models":[8],"trained":[9],"on":[10,207],"specific":[11],"source":[12],"domains":[13,20,44],"struggle":[14],"to":[15,17,22,54,69,82,106,138,181,200],"generalize":[16],"unseen":[18],"target":[19],"due":[21,53],"variations":[23],"distributions,":[25],"data":[26,103,179,227],"collection":[27],"conditions,":[28,172],"and":[29,99,142,194,237],"biases.":[30],"These":[31],"differences,":[32],"known":[33],"as":[34,83,90],"domain":[35],"shifts,":[36],"can":[37],"considerably":[38],"impact":[39],"model":[40],"performance":[41],"facing":[43],"not":[45],"encountered":[46],"during":[47],"training.":[48],"This":[49],"circumstance":[50],"arises":[51],"partially":[52],"the":[55,67,111,118,125,153,159,168,201,208,223],"limitations":[56],"of":[57,120,127,155,162,170,234],"commonly":[58,80],"used":[59],"optimizers":[60],"like":[61],"SGD":[62],"or":[63],"ADAM,":[64],"which":[65,164],"lack":[66],"capability":[68],"preferentially":[70],"converge":[71],"towards":[72],"optimal":[73],"points":[74],"characterized":[75],"by":[76,104],"high":[77],"capacity,":[79],"referred":[81],"flat":[84,108],"minima.":[85],"Sharpness-Aware":[86],"Minimization":[87],"(SAM)":[88],"emerges":[89],"a":[91],"powerful":[92],"tool":[93],"for":[94,225],"facilitating":[95],"independent":[98],"identically":[100],"distributed":[101],"(i.i.d)":[102],"aiming":[105],"find":[107],"minima":[109],"loss":[112],"landscape":[113],"that":[114,188],"remain":[115],"robust":[116],"face":[119],"input":[121],"sample":[122],"perturbations.":[123],"Among":[124],"variants":[126],"SAM,":[128],"one":[129],"notable":[130],"variant":[131],"is":[132],"ASAM,":[133,163],"an":[134,231],"adaptive":[135],"version":[136],"designed":[137],"withstand":[139],"parameter":[140],"re-scaling":[141],"ensure":[143],"robustness.":[144,184],"In":[145],"this":[146,173],"study,":[147],"our":[148],"primary":[149],"focus":[150],"lies":[151],"utilization":[154,161],"ASAM.":[156],"Diverging":[157],"from":[158],"conventional":[160],"predominantly":[165],"functions":[166],"within":[167],"confines":[169],"i.i.d":[171],"paper":[174],"applies":[175],"ASAM":[176,189,229],"OoD":[178],"scenarios":[180],"evaluate":[182],"its":[183],"Our":[185,204],"findings":[186],"reveal":[187],"exhibits":[190],"stable":[191],"training":[192],"behavior":[193],"superior":[195],"capabilities":[197],"compared":[199],"Adam":[202],"optimizer.":[203],"experiments,":[205],"conducted":[206],"NICO":[209],"dataset":[210],"encompassing":[211],"multiple":[212],"domains,":[213],"showcase":[214],"ASAM\u2019s":[215],"remarkable":[216],"performance,":[217],"surpassing":[218],"other":[219],"state-of-the-art":[220],"methods":[221],"without":[222],"need":[224],"intricate":[226],"augmentation.":[228],"achieves":[230],"accuracy":[232],"rate":[233],"87.25%":[235],"(Animal)":[236],"80.79%":[238],"(Vehicle).":[239]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}