{"id":"https://openalex.org/W4289655240","doi":"https://doi.org/10.1109/isit50566.2022.9834618","title":"A Mathematical Framework to Characterize the Dependency Structures in Multimodal Learning with Minimax Principle","display_name":"A Mathematical Framework to Characterize the Dependency Structures in Multimodal Learning with Minimax Principle","publication_year":2022,"publication_date":"2022-06-26","ids":{"openalex":"https://openalex.org/W4289655240","doi":"https://doi.org/10.1109/isit50566.2022.9834618"},"language":"en","primary_location":{"id":"doi:10.1109/isit50566.2022.9834618","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isit50566.2022.9834618","pdf_url":null,"source":{"id":"https://openalex.org/S4363604560","display_name":"2022 IEEE International Symposium on Information Theory (ISIT)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Symposium on Information Theory (ISIT)","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/A5051403008","display_name":"Tianren Peng","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114105","display_name":"Tsinghua\u2013Berkeley Shenzhen Institute","ror":"https://ror.org/02hhwwz98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114105","https://openalex.org/I95457486","https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Tianren Peng","raw_affiliation_strings":["Tsinghua-Berkeley Shenzhen Institute,DSIT Research Center,Shenzhen,China,518055"],"affiliations":[{"raw_affiliation_string":"Tsinghua-Berkeley Shenzhen Institute,DSIT Research Center,Shenzhen,China,518055","institution_ids":["https://openalex.org/I4210114105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101800202","display_name":"Weida Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114105","display_name":"Tsinghua\u2013Berkeley Shenzhen Institute","ror":"https://ror.org/02hhwwz98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114105","https://openalex.org/I95457486","https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weida Wang","raw_affiliation_strings":["Tsinghua-Berkeley Shenzhen Institute,DSIT Research Center,Shenzhen,China,518055"],"affiliations":[{"raw_affiliation_string":"Tsinghua-Berkeley Shenzhen Institute,DSIT Research Center,Shenzhen,China,518055","institution_ids":["https://openalex.org/I4210114105"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088293566","display_name":"Shao\u2010Lun Huang","orcid":"https://orcid.org/0000-0003-2827-4022"},"institutions":[{"id":"https://openalex.org/I4210114105","display_name":"Tsinghua\u2013Berkeley Shenzhen Institute","ror":"https://ror.org/02hhwwz98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114105","https://openalex.org/I95457486","https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shao-Lun Huang","raw_affiliation_strings":["Tsinghua-Berkeley Shenzhen Institute,DSIT Research Center,Shenzhen,China,518055"],"affiliations":[{"raw_affiliation_string":"Tsinghua-Berkeley Shenzhen Institute,DSIT Research Center,Shenzhen,China,518055","institution_ids":["https://openalex.org/I4210114105"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5051403008"],"corresponding_institution_ids":["https://openalex.org/I4210114105"],"apc_list":null,"apc_paid":null,"fwci":0.1046,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.27879366,"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":"1489","last_page":"1494"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9661999940872192,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9661999940872192,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9272000193595886,"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/T12135","display_name":"Fuzzy Systems and Optimization","score":0.9258999824523926,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.8403205275535583},{"id":"https://openalex.org/keywords/minimax","display_name":"Minimax","score":0.7629258632659912},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.6757783889770508},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6022192239761353},{"id":"https://openalex.org/keywords/conditional-probability-distribution","display_name":"Conditional probability distribution","score":0.5440977215766907},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5397208333015442},{"id":"https://openalex.org/keywords/cardinality","display_name":"Cardinality (data modeling)","score":0.45442748069763184},{"id":"https://openalex.org/keywords/conditional-expectation","display_name":"Conditional expectation","score":0.4457986056804657},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4148690104484558},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.37841111421585083},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3452182412147522},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.33707910776138306},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.15889251232147217},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.14739808440208435}],"concepts":[{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.8403205275535583},{"id":"https://openalex.org/C149728462","wikidata":"https://www.wikidata.org/wiki/Q751319","display_name":"Minimax","level":2,"score":0.7629258632659912},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.6757783889770508},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6022192239761353},{"id":"https://openalex.org/C43555835","wikidata":"https://www.wikidata.org/wiki/Q2300258","display_name":"Conditional probability distribution","level":2,"score":0.5440977215766907},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5397208333015442},{"id":"https://openalex.org/C87117476","wikidata":"https://www.wikidata.org/wiki/Q362383","display_name":"Cardinality (data modeling)","level":2,"score":0.45442748069763184},{"id":"https://openalex.org/C186215838","wikidata":"https://www.wikidata.org/wiki/Q772232","display_name":"Conditional expectation","level":2,"score":0.4457986056804657},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4148690104484558},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.37841111421585083},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3452182412147522},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.33707910776138306},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.15889251232147217},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.14739808440208435}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/isit50566.2022.9834618","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isit50566.2022.9834618","pdf_url":null,"source":{"id":"https://openalex.org/S4363604560","display_name":"2022 IEEE International Symposium on Information Theory (ISIT)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Symposium on Information Theory (ISIT)","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":22,"referenced_works":["https://openalex.org/W189514790","https://openalex.org/W1933349210","https://openalex.org/W2025137987","https://openalex.org/W2045656688","https://openalex.org/W2049898120","https://openalex.org/W2184188583","https://openalex.org/W2210387432","https://openalex.org/W2619383789","https://openalex.org/W2883409523","https://openalex.org/W2898130205","https://openalex.org/W2937019265","https://openalex.org/W2963767133","https://openalex.org/W2964346351","https://openalex.org/W3093521632","https://openalex.org/W3147919432","https://openalex.org/W3213681123","https://openalex.org/W4239715372","https://openalex.org/W4293404332","https://openalex.org/W6607642809","https://openalex.org/W6686207219","https://openalex.org/W6761139768","https://openalex.org/W6804470225"],"related_works":["https://openalex.org/W3168953348","https://openalex.org/W4298857702","https://openalex.org/W2796775270","https://openalex.org/W2071970553","https://openalex.org/W4238858747","https://openalex.org/W2592623155","https://openalex.org/W2592465853","https://openalex.org/W2963081535","https://openalex.org/W4233361406","https://openalex.org/W2046750897"],"abstract_inverted_index":{"Multimodal":[0],"learning":[1,97],"is":[2,32,36,70,91,111,148],"an":[3,67],"increasingly":[4],"important":[5],"research":[6],"topic.":[7],"Exploiting":[8],"conditional":[9,42,106,125],"dependency":[10,43,102,126],"across":[11],"multiple":[12],"modalities":[13],"has":[14],"been":[15],"shown":[16],"useful":[17],"for":[18],"estimating":[19],"of":[20,29,76,95,118,123,131,154],"the":[21,27,56,61,73,77,84,88,96,100,105,116,121,124,129,145,151,155],"multimodal":[22],"joint":[23],"distribution,":[24],"especially":[25],"when":[26],"number":[28,117],"training":[30,119],"samples":[31],"insufficient.":[33],"However,":[34],"it":[35],"difficult":[37],"to":[38,72,113,139,150],"theoretically":[39],"characterize":[40],"such":[41],"structure.":[44],"To":[45],"address":[46],"this":[47],"issue,":[48],"we":[49,65],"establish":[50],"a":[51,80,92],"mathematical":[52],"framework":[53],"and":[54,104,128],"formulate":[55],"estimation":[57],"problem":[58,78],"based":[59],"on":[60,83],"minimax":[62],"principle.":[63],"Then,":[64],"propose":[66],"estimator":[68,90,147],"which":[69],"close":[71,149],"analytical":[74],"solution":[75,153],"under":[79],"mild":[81],"assumption":[82],"sample":[85],"size.":[86],"Moreover,":[87],"proposed":[89,146],"linear":[93],"combination":[94],"results":[98,143],"from":[99],"true":[101],"structure":[103],"one.":[107],"The":[108],"combining":[109],"coefficient":[110],"related":[112],"three":[114],"aspects:":[115],"samples,":[120],"fitness":[122],"structure,":[127],"cardinality":[130],"each":[132],"modality.":[133],"Finally,":[134],"numerical":[135],"simulations":[136],"are":[137],"provided":[138],"verify":[140],"our":[141],"theoretical":[142],"that":[144],"optimal":[152],"formulated":[156],"problem.":[157]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-25T13:04:00.132906","created_date":"2025-10-10T00:00:00"}