{"id":"https://openalex.org/W2117902970","doi":"https://doi.org/10.1109/tit.2012.2222343","title":"Classification of Homogeneous Data With Large Alphabets","display_name":"Classification of Homogeneous Data With Large Alphabets","publication_year":2012,"publication_date":"2012-10-25","ids":{"openalex":"https://openalex.org/W2117902970","doi":"https://doi.org/10.1109/tit.2012.2222343","mag":"2117902970"},"language":"en","primary_location":{"id":"doi:10.1109/tit.2012.2222343","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tit.2012.2222343","pdf_url":null,"source":{"id":"https://openalex.org/S4502562","display_name":"IEEE Transactions on Information Theory","issn_l":"0018-9448","issn":["0018-9448","1557-9654"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Information Theory","raw_type":"journal-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/A5088724430","display_name":"Benjamin G. Kelly","orcid":null},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Benjamin G. Kelly","raw_affiliation_strings":["School of Electrical and Computer Engineering, Cornell University, Ithaca, NY, USA","Sch. of Electr. & Comput. Eng., Cornell Univ., Ithaca, NY, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, Cornell University, Ithaca, NY, USA","institution_ids":["https://openalex.org/I205783295"]},{"raw_affiliation_string":"Sch. of Electr. & Comput. Eng., Cornell Univ., Ithaca, NY, USA#TAB#","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073557148","display_name":"Aaron B. Wagner","orcid":"https://orcid.org/0000-0001-9127-0089"},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aaron B. Wagner","raw_affiliation_strings":["School of Electrical and Computer Engineering, Cornell University, Ithaca, NY, USA","Sch. of Electr. & Comput. Eng., Cornell Univ., Ithaca, NY, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, Cornell University, Ithaca, NY, USA","institution_ids":["https://openalex.org/I205783295"]},{"raw_affiliation_string":"Sch. of Electr. & Comput. Eng., Cornell Univ., Ithaca, NY, USA#TAB#","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035707756","display_name":"Thitidej Tularak","orcid":null},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Thitidej Tularak","raw_affiliation_strings":["School of Electrical and Computer Engineering, Cornell University, Ithaca, NY, USA","Sch. of Electr. & Comput. Eng., Cornell Univ., Ithaca, NY, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, Cornell University, Ithaca, NY, USA","institution_ids":["https://openalex.org/I205783295"]},{"raw_affiliation_string":"Sch. of Electr. & Comput. Eng., Cornell Univ., Ithaca, NY, USA#TAB#","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053980484","display_name":"Pramod Viswanath","orcid":"https://orcid.org/0000-0003-3171-8667"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pramod Viswanath","raw_affiliation_strings":["Coordinated Science Laboratory, University of Illinois at Urbana-Champaign, Urbana-Champaign, IL, USA","[Coordinated Science Lab, University of Illinois at Urbana\u2013Champaign, Urbana, IL, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Coordinated Science Laboratory, University of Illinois at Urbana-Champaign, Urbana-Champaign, IL, USA","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"[Coordinated Science Lab, University of Illinois at Urbana\u2013Champaign, Urbana, IL, USA]","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.2164,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.92364184,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"59","issue":"2","first_page":"782","last_page":"795"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.9998999834060669,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9998999834060669,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9998000264167786,"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/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.9973000288009644,"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/alphabet","display_name":"Alphabet","score":0.8238292932510376},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.6393359303474426},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5615071654319763},{"id":"https://openalex.org/keywords/homogeneous","display_name":"Homogeneous","score":0.5494297742843628},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.5306790471076965},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.525047779083252},{"id":"https://openalex.org/keywords/probability-distribution","display_name":"Probability distribution","score":0.5227325558662415},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.41816824674606323},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3797316551208496},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.337686687707901},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.26673799753189087}],"concepts":[{"id":"https://openalex.org/C112876837","wikidata":"https://www.wikidata.org/wiki/Q837518","display_name":"Alphabet","level":2,"score":0.8238292932510376},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.6393359303474426},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5615071654319763},{"id":"https://openalex.org/C66882249","wikidata":"https://www.wikidata.org/wiki/Q169336","display_name":"Homogeneous","level":2,"score":0.5494297742843628},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5306790471076965},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.525047779083252},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.5227325558662415},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.41816824674606323},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3797316551208496},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.337686687707901},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.26673799753189087},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tit.2012.2222343","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tit.2012.2222343","pdf_url":null,"source":{"id":"https://openalex.org/S4502562","display_name":"IEEE Transactions on Information Theory","issn_l":"0018-9448","issn":["0018-9448","1557-9654"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Information Theory","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.413.4747","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.413.4747","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ifp.illinois.edu/~pramodv/pubs/KWTV10.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8299999833106995}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W989791606","https://openalex.org/W1460189015","https://openalex.org/W1501167079","https://openalex.org/W1515002134","https://openalex.org/W1535258871","https://openalex.org/W1549664537","https://openalex.org/W1560724230","https://openalex.org/W1565802011","https://openalex.org/W1928812145","https://openalex.org/W1971588397","https://openalex.org/W1980191583","https://openalex.org/W1992068214","https://openalex.org/W2021553591","https://openalex.org/W2025814013","https://openalex.org/W2033103765","https://openalex.org/W2040820014","https://openalex.org/W2050959052","https://openalex.org/W2076837681","https://openalex.org/W2104648144","https://openalex.org/W2114495039","https://openalex.org/W2115054880","https://openalex.org/W2130275649","https://openalex.org/W2154376008","https://openalex.org/W2159784709","https://openalex.org/W2159902206","https://openalex.org/W2179067121","https://openalex.org/W2182991033","https://openalex.org/W2187447858","https://openalex.org/W2963752288","https://openalex.org/W3104678156","https://openalex.org/W3195149063","https://openalex.org/W4294554802","https://openalex.org/W4294841944","https://openalex.org/W6685779351","https://openalex.org/W6685787598","https://openalex.org/W6686954971"],"related_works":["https://openalex.org/W1978042415","https://openalex.org/W3154129246","https://openalex.org/W3102632868","https://openalex.org/W3134723363","https://openalex.org/W1994589449","https://openalex.org/W2371101167","https://openalex.org/W1998707102","https://openalex.org/W2032649343","https://openalex.org/W2327776733","https://openalex.org/W2112146432"],"abstract_inverted_index":{"Given":[0],"training":[1],"sequences":[2],"generated":[3,25],"by":[4],"two":[5],"distinct,":[6],"but":[7],"unknown,":[8],"distributions":[9,44,65],"on":[10],"a":[11,21],"common":[12],"alphabet,":[13],"we":[14,54,93],"study":[15],"the":[16,28,42,56,63,69,76,80,86,104,109,130],"problem":[17],"of":[18,52,85],"determining":[19],"whether":[20],"third":[22],"sequence":[23],"was":[24],"according":[26],"to":[27,47,59,66],"first":[29],"or":[30],"second":[31],"distribution.":[32],"To":[33],"model":[34],"sources":[35],"such":[36],"as":[37],"natural":[38],"language,":[39],"for":[40],"which":[41,79],"underlying":[43,81],"are":[45,83,121,126],"difficult":[46],"learn":[48],"from":[49],"realistic":[50],"amounts":[51],"data,":[53],"allow":[55],"alphabet":[57,105,131],"size":[58],"grow":[60],"and":[61,89,101],"therefore":[62],"probability":[64],"change":[67],"with":[68,108],"block":[70,110],"length.":[71,111],"Our":[72],"primary":[73],"focus":[74],"is":[75,98],"situation":[77],"in":[78,90,123],"probabilities":[82],"all":[84],"same":[87],"order,":[88],"this":[91],"regime,":[92],"show":[94,114],"that":[95,115,124],"consistent":[96,127],"classification":[97],"possible":[99],"if":[100,103,129],"only":[102,128],"grows":[106,132],"subquadratically":[107],"We":[112],"also":[113],"some":[116],"commonly":[117],"used":[118],"statistical":[119],"tests":[120],"suboptimal":[122],"they":[125],"sublinearly.":[133]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":5},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}