{"id":"https://openalex.org/W4375869352","doi":"https://doi.org/10.1109/icassp49357.2023.10095775","title":"Distributionally Robust Multiclass Classification and Applications in Deep Image Classifiers","display_name":"Distributionally Robust Multiclass Classification and Applications in Deep Image Classifiers","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375869352","doi":"https://doi.org/10.1109/icassp49357.2023.10095775"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095775","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095775","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5067887830","display_name":"Ruidi Chen","orcid":"https://orcid.org/0000-0002-1508-1742"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ruidi Chen","raw_affiliation_strings":["Amazon SCOT"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon SCOT","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068903474","display_name":"Boran Hao","orcid":"https://orcid.org/0000-0001-7922-0513"},"institutions":[{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Boran Hao","raw_affiliation_strings":["Boston University,Department of Electrical and Computer Engineering","Department of Electrical and Computer Engineering, Boston University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Boston University,Department of Electrical and Computer Engineering","institution_ids":["https://openalex.org/I111088046"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Boston University","institution_ids":["https://openalex.org/I111088046"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075696701","display_name":"Ioannis Ch. Paschalidis","orcid":"https://orcid.org/0000-0002-3343-2913"},"institutions":[{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ioannis Ch. Paschalidis","raw_affiliation_strings":["Boston University,Department of Electrical and Computer Engineering","Department of Electrical and Computer Engineering, Boston University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Boston University,Department of Electrical and Computer Engineering","institution_ids":["https://openalex.org/I111088046"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Boston University","institution_ids":["https://openalex.org/I111088046"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.6674,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.86094995,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"2"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9983000159263611,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9983000159263611,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9585000276565552,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9567999839782715,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/mnist-database","display_name":"MNIST database","score":0.7646359205245972},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6358195543289185},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5681633353233337},{"id":"https://openalex.org/keywords/outlier","display_name":"Outlier","score":0.5442651510238647},{"id":"https://openalex.org/keywords/multiclass-classification","display_name":"Multiclass classification","score":0.5145341753959656},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.4708917737007141},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4663255512714386},{"id":"https://openalex.org/keywords/wasserstein-metric","display_name":"Wasserstein metric","score":0.4578815996646881},{"id":"https://openalex.org/keywords/ambiguity","display_name":"Ambiguity","score":0.4529232084751129},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.45126038789749146},{"id":"https://openalex.org/keywords/robust-optimization","display_name":"Robust optimization","score":0.4302392303943634},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4006623327732086},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3803999125957489},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.37031835317611694},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.27328208088874817},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.13638392090797424}],"concepts":[{"id":"https://openalex.org/C190502265","wikidata":"https://www.wikidata.org/wiki/Q17069496","display_name":"MNIST database","level":3,"score":0.7646359205245972},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6358195543289185},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5681633353233337},{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.5442651510238647},{"id":"https://openalex.org/C123860398","wikidata":"https://www.wikidata.org/wiki/Q6934605","display_name":"Multiclass classification","level":3,"score":0.5145341753959656},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.4708917737007141},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4663255512714386},{"id":"https://openalex.org/C2777634741","wikidata":"https://www.wikidata.org/wiki/Q768993","display_name":"Wasserstein metric","level":2,"score":0.4578815996646881},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.4529232084751129},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.45126038789749146},{"id":"https://openalex.org/C193254401","wikidata":"https://www.wikidata.org/wiki/Q2160088","display_name":"Robust optimization","level":2,"score":0.4302392303943634},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4006623327732086},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3803999125957489},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.37031835317611694},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.27328208088874817},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.13638392090797424},{"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/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095775","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095775","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:null:2144/48795","is_oa":false,"landing_page_url":"http://doi.org/10.1109/icassp49357.2023.10095775","pdf_url":null,"source":{"id":"https://openalex.org/S4306402384","display_name":"OpenBU (Boston University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I111088046","host_organization_name":"Boston University","host_organization_lineage":["https://openalex.org/I111088046"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"Conference materials"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320309565","display_name":"Boston University","ror":"https://ror.org/05qwgg493"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1999913571","https://openalex.org/W2048679451","https://openalex.org/W2102605133","https://openalex.org/W2116200501","https://openalex.org/W2117173631","https://openalex.org/W2125417745","https://openalex.org/W2543927648","https://openalex.org/W2765622255","https://openalex.org/W2781132081","https://openalex.org/W2893687496","https://openalex.org/W2963450292","https://openalex.org/W2963772730","https://openalex.org/W3004623877","https://openalex.org/W3094502228","https://openalex.org/W3118608800","https://openalex.org/W4206328009","https://openalex.org/W4231382867","https://openalex.org/W4288346299","https://openalex.org/W4293846201","https://openalex.org/W4306353376","https://openalex.org/W6638102014","https://openalex.org/W6675026286","https://openalex.org/W6677103149","https://openalex.org/W6682388183","https://openalex.org/W6703180097","https://openalex.org/W6739868092","https://openalex.org/W6746908489","https://openalex.org/W6755506522","https://openalex.org/W6763086904","https://openalex.org/W6784333009"],"related_works":["https://openalex.org/W2963450292","https://openalex.org/W3212059471","https://openalex.org/W2970846301","https://openalex.org/W3148598382","https://openalex.org/W4386362533","https://openalex.org/W4292217711","https://openalex.org/W2975160718","https://openalex.org/W3164608506","https://openalex.org/W4319303015","https://openalex.org/W3015523332"],"abstract_inverted_index":{"We":[0,52,71,95],"develop":[1],"a":[2,24,30,58,65,145],"Distributionally":[3],"Robust":[4],"Optimization":[5],"(DRO)":[6],"formulation":[7,56],"for":[8,76],"Multiclass":[9],"Logistic":[10],"Regression":[11],"(MLR),":[12],"which":[13],"could":[14],"tolerate":[15],"data":[16],"contaminated":[17],"by":[18,129,135,143],"outliers.":[19],"The":[20],"DRO":[21,55],"framework":[22],"uses":[23],"probabilistic":[25],"ambiguity":[26],"set":[27,44],"defined":[28],"as":[29],"ball":[31],"of":[32,41,48,67,87],"distributions":[33],"that":[34],"are":[35],"close":[36],"to":[37,79,110,131,137],"the":[38,42,46,49,54,68,77,85,88,92,97,117],"empirical":[39],"distribution":[40],"training":[43,148],"in":[45,90,100,125],"sense":[47],"Wasserstein":[50],"metric.":[51],"relax":[53],"into":[57],"regularized":[59],"learning":[60],"problem":[61],"whose":[62],"regularizer":[63,89],"is":[64],"norm":[66],"coefficient":[69],"matrix.":[70],"establish":[72],"out-of-sample":[73],"performance":[74],"guarantees":[75],"solutions":[78],"our":[80],"model,":[81],"offering":[82],"insights":[83],"on":[84],"role":[86],"controlling":[91],"prediction":[93],"error.":[94],"apply":[96],"proposed":[98],"method":[99],"rendering":[101],"deep":[102],"Vision":[103],"Transformer":[104],"(ViT)-based":[105],"[1]":[106],"image":[107],"classifiers":[108],"robust":[109],"random":[111,147],"and":[112,119,133],"adversarial":[113],"attacks.":[114],"Specifically,":[115],"using":[116],"MNIST":[118],"CIFAR-10":[120],"datasets,":[121],"we":[122],"demonstrate":[123],"reductions":[124],"test":[126],"error":[127],"rate":[128],"up":[130,136],"83.5%":[132],"loss":[134],"91.3%":[138],"compared":[139],"with":[140],"baseline":[141],"methods,":[142],"adopting":[144],"novel":[146],"method.":[149]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1}],"updated_date":"2026-08-25T07:29:55.448023","created_date":"2025-10-10T00:00:00"}