{"id":"https://openalex.org/W4415366986","doi":"https://doi.org/10.1109/isit63088.2025.11195224","title":"Learning and Generalization with Mixture Data","display_name":"Learning and Generalization with Mixture Data","publication_year":2025,"publication_date":"2025-06-22","ids":{"openalex":"https://openalex.org/W4415366986","doi":"https://doi.org/10.1109/isit63088.2025.11195224"},"language":null,"primary_location":{"id":"doi:10.1109/isit63088.2025.11195224","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isit63088.2025.11195224","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 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/A5109104268","display_name":"Harsh Vardhan","orcid":null},"institutions":[{"id":"https://openalex.org/I160856358","display_name":"University of San Diego","ror":"https://ror.org/03jbbze48","country_code":"US","type":"education","lineage":["https://openalex.org/I160856358"]},{"id":"https://openalex.org/I36258959","display_name":"University of California, San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Harsh Vardhan","raw_affiliation_strings":["University of California,Computer Science & Engineering,San Diego,CA,USA"],"affiliations":[{"raw_affiliation_string":"University of California,Computer Science & Engineering,San Diego,CA,USA","institution_ids":["https://openalex.org/I36258959","https://openalex.org/I160856358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101622808","display_name":"Avishek Ghosh","orcid":"https://orcid.org/0000-0002-6548-6692"},"institutions":[{"id":"https://openalex.org/I162827531","display_name":"Indian Institute of Technology Bombay","ror":"https://ror.org/02qyf5152","country_code":"IN","type":"education","lineage":["https://openalex.org/I162827531"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Avishek Ghosh","raw_affiliation_strings":["Indian Institute of Technology,Computer Science & Engineering,Mumbai,Maharashtra,India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology,Computer Science & Engineering,Mumbai,Maharashtra,India","institution_ids":["https://openalex.org/I162827531"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051046818","display_name":"Arya Mazumdar","orcid":"https://orcid.org/0000-0003-4605-7996"},"institutions":[{"id":"https://openalex.org/I4210107081","display_name":"Xenobe Research Institute","ror":"https://ror.org/01pb5g963","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210107081"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Arya Mazumdar","raw_affiliation_strings":["Institute University of California,Halıcıoğlu Data Science,San Diego,CA,USA"],"affiliations":[{"raw_affiliation_string":"Institute University of California,Halıcıoğlu Data Science,San Diego,CA,USA","institution_ids":["https://openalex.org/I4210107081"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5109104268"],"corresponding_institution_ids":["https://openalex.org/I160856358","https://openalex.org/I36258959"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.15409424,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.798799991607666,"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/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.798799991607666,"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/T12368","display_name":"Grey System Theory Applications","score":0.6951000094413757,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.7491000294685364},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.6098999977111816},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.4636000096797943},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.4521999955177307},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.4334999918937683},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.38339999318122864},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.37880000472068787},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.36880001425743103},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.3605000078678131}],"concepts":[{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.7491000294685364},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.6098999977111816},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.4636000096797943},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.46070000529289246},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.4521999955177307},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.4334999918937683},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.42890000343322754},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39820000529289246},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.38339999318122864},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.37880000472068787},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.36880001425743103},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.3605000078678131},{"id":"https://openalex.org/C2779915298","wikidata":"https://www.wikidata.org/wiki/Q7604400","display_name":"Statistical learning theory","level":3,"score":0.3407999873161316},{"id":"https://openalex.org/C57869625","wikidata":"https://www.wikidata.org/wiki/Q1783502","display_name":"Rate of convergence","level":3,"score":0.335999995470047},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3359000086784363},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.328900009393692},{"id":"https://openalex.org/C21080849","wikidata":"https://www.wikidata.org/wiki/Q13611879","display_name":"Data point","level":2,"score":0.32350000739097595},{"id":"https://openalex.org/C48921125","wikidata":"https://www.wikidata.org/wiki/Q10861030","display_name":"Linear regression","level":2,"score":0.32030001282691956},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.3158999979496002},{"id":"https://openalex.org/C2781147490","wikidata":"https://www.wikidata.org/wiki/Q5156808","display_name":"Compositional data","level":2,"score":0.3075999915599823},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.30390000343322754},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.29809999465942383},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.2858999967575073},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.28380000591278076},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.26910001039505005},{"id":"https://openalex.org/C112680207","wikidata":"https://www.wikidata.org/wiki/Q714886","display_name":"Regular polygon","level":2,"score":0.2687999904155731},{"id":"https://openalex.org/C56672385","wikidata":"https://www.wikidata.org/wiki/Q17157111","display_name":"Mixture distribution","level":3,"score":0.26460000872612},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2630000114440918},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.2542000114917755}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/isit63088.2025.11195224","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isit63088.2025.11195224","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Symposium on Information Theory (ISIT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3041620093","display_name":null,"funder_award_id":"2217058,2112665","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1956647075","https://openalex.org/W1974648697","https://openalex.org/W2512971201","https://openalex.org/W2962737134","https://openalex.org/W2964256738","https://openalex.org/W3080110460","https://openalex.org/W4211030719","https://openalex.org/W4302561155"],"related_works":[],"abstract_inverted_index":{"In":[0,53,116,150],"many,":[1],"if":[2],"not":[3],"most,":[4],"machine":[5],"learning":[6],"applications":[7],"the":[8,33,74,77,82,88,101,104,120,124,129,172,182,189,192,210,222],"training":[9],"data":[10,47,64],"is":[11,28,48,65],"naturally":[12],"heterogeneous":[13,46],"(e.g.":[14],"federated":[15],"learning,":[16],"adversarial":[17],"attacks":[18],"and":[19,60,128,146,159,167,174,216],"domain":[20],"adaptation":[21],"in":[22,36,79,225],"neural":[23],"net":[24],"training).":[25],"Data":[26],"heterogeneity":[27,75],"identified":[29],"as":[30,92,109,140,142,181],"one":[31],"of":[32,76,81,87,96,138,212,227],"major":[34],"challenges":[35],"modern":[37],"day":[38],"large-scale":[39],"learning.":[40,115],"A":[41],"classical":[42,125],"way":[43],"to":[44,152,170],"represent":[45],"via":[49],"a":[50,68,93,110,206,218],"mixture":[51,69,78,105,137,165],"model.":[52],"this":[54,97],"paper,":[55,98],"we":[56,99,118,155],"study":[57,119],"generalization":[58,121,173,223],"performance":[59,122],"statistical":[61,130],"rates":[62,132,176],"when":[63],"sampled":[66],"from":[67],"distribution.":[70],"We":[71,178,203],"first":[72],"characterize":[73,100],"terms":[80,226],"pairwise":[83,193],"total":[84,194],"variation":[85,195],"distance":[86,196],"sub-population":[89],"distributions.":[90],"Thereafter,":[91],"central":[94],"theme":[95],"range":[102],"where":[103],"may":[106],"be":[107],"treated":[108],"single":[111],"(homogeneous)":[112],"distribution":[113],"for":[114,133,209],"particular,":[117],"under":[123],"PAC":[126],"framework":[127],"error":[131,224],"parametric":[134],"(linear":[135],"regression,":[136],"hyperplanes)":[139],"well":[141],"non-parametric":[143],"(Lipschitz,":[144],"convex":[145],"H\u00f6lder-smooth)":[147],"regression":[148,215],"problems.":[149],"order":[151],"do":[153,205],"this,":[154],"obtain":[156],"Rademacher":[157],"complexity":[158,162],"(local)":[160],"Gaussian":[161],"bounds":[163],"with":[164],"data,":[166],"apply":[168],"them":[169],"get":[171,186],"convergence":[175],"respectively.":[177],"observe":[179],"that":[180],"(regression)":[183],"function":[184],"classes":[185],"more":[187],"complex,":[188],"requirement":[190],"on":[191,221],"gets":[197],"stringent,":[198],"which":[199],"matches":[200],"our":[201],"intuition.":[202],"also":[204],"finer":[207],"analysis":[208],"case":[211],"mixed":[213],"linear":[214],"provide":[217],"tight":[219],"bound":[220],"heterogeneity.":[228]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-21T00:00:00"}