{"id":"https://openalex.org/W2169991579","doi":"https://doi.org/10.1109/isit.2004.1365341","title":"Algorithms for modeling distributions over large alphabets","display_name":"Algorithms for modeling distributions over large alphabets","publication_year":2004,"publication_date":"2004-12-23","ids":{"openalex":"https://openalex.org/W2169991579","doi":"https://doi.org/10.1109/isit.2004.1365341","mag":"2169991579"},"language":"en","primary_location":{"id":"doi:10.1109/isit.2004.1365341","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isit.2004.1365341","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Symposium onInformation Theory, 2004. ISIT 2004. Proceedings.","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/A5012034611","display_name":"Alon Orlitsky","orcid":null},"institutions":[{"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":false,"raw_author_name":"A. Orlitsky","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of California, San Diego, La Jolla, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of California, San Diego, La Jolla, CA, USA","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030721514","display_name":"S. Sajama","orcid":null},"institutions":[{"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":false,"raw_author_name":"S. Sajama","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of California, San Diego, La Jolla, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of California, San Diego, La Jolla, CA, USA","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030506196","display_name":"Narayana Santhanam","orcid":"https://orcid.org/0000-0001-6515-6311"},"institutions":[{"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":false,"raw_author_name":"N.P. Santhanam","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of California, San Diego, La Jolla, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of California, San Diego, La Jolla, CA, USA","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004200489","display_name":"K. Viswanathan","orcid":"https://orcid.org/0009-0001-0550-5652"},"institutions":[{"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":false,"raw_author_name":"K. Viswanathan","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of California, San Diego, La Jolla, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of California, San Diego, La Jolla, CA, USA","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"last","author":{"id":null,"display_name":"Junan Zhang","orcid":null},"institutions":[{"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":false,"raw_author_name":"Junan Zhang","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of California, San Diego, La Jolla, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of California, San Diego, La Jolla, CA, USA","institution_ids":["https://openalex.org/I36258959"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4626,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.77279951,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"304","last_page":"304"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":1.0,"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/T11269","display_name":"Algorithms and Data Compression","score":1.0,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9933000206947327,"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":0.9923999905586243,"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/estimator","display_name":"Estimator","score":0.7386574745178223},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6207123398780823},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.607634961605072},{"id":"https://openalex.org/keywords/alphabet","display_name":"Alphabet","score":0.5931338667869568},{"id":"https://openalex.org/keywords/probability-distribution","display_name":"Probability distribution","score":0.4946560561656952},{"id":"https://openalex.org/keywords/distribution","display_name":"Distribution (mathematics)","score":0.49356377124786377},{"id":"https://openalex.org/keywords/maximum-likelihood","display_name":"Maximum likelihood","score":0.49176838994026184},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.44639337062835693},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.3060606122016907},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.29940077662467957}],"concepts":[{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.7386574745178223},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6207123398780823},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.607634961605072},{"id":"https://openalex.org/C112876837","wikidata":"https://www.wikidata.org/wiki/Q837518","display_name":"Alphabet","level":2,"score":0.5931338667869568},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.4946560561656952},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.49356377124786377},{"id":"https://openalex.org/C49781872","wikidata":"https://www.wikidata.org/wiki/Q1045555","display_name":"Maximum likelihood","level":2,"score":0.49176838994026184},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.44639337062835693},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.3060606122016907},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.29940077662467957},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/isit.2004.1365341","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isit.2004.1365341","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Symposium onInformation Theory, 2004. ISIT 2004. Proceedings.","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":5,"referenced_works":["https://openalex.org/W2056760934","https://openalex.org/W2095306947","https://openalex.org/W2106981684","https://openalex.org/W2127831256","https://openalex.org/W4253764066"],"related_works":["https://openalex.org/W4287880334","https://openalex.org/W4366700029","https://openalex.org/W4285230481","https://openalex.org/W2074481494","https://openalex.org/W4385769873","https://openalex.org/W4281634296","https://openalex.org/W4319161863","https://openalex.org/W2371687270","https://openalex.org/W4311888330","https://openalex.org/W4250156143"],"abstract_inverted_index":{"We":[0,47],"consider":[1],"the":[2,15,38,41,44,59,63],"problem":[3],"of":[4,17,43],"modeling":[5],"a":[6],"distribution":[7,39,61],"whose":[8],"alphabet":[9],"size":[10],"is":[11,21],"large":[12],"relative":[13],"to":[14],"amount":[16],"observed":[18],"data.":[19],"It":[20],"well":[22,31,65,76],"known":[23],"that":[24,33,58,70],"conventional":[25],"maximum-likelihood":[26],"estimates":[27],"do":[28],"not":[29],"perform":[30],"in":[32],"regime.":[34],"Instead,":[35],"we":[36],"find":[37],"maximizing":[40],"probability":[42],"data's":[45],"pattern.":[46],"derive":[48],"an":[49],"efficient":[50],"algorithm":[51],"for":[52,82],"approximating":[53],"this":[54],"distribution.":[55],"Simulations":[56],"show":[57],"computed":[60],"models":[62],"data":[64,73],"and":[66],"yields":[67],"general":[68],"estimators":[69,79],"evaluate":[71],"various":[72],"attributes":[74],"as":[75,77],"specific":[78],"designed":[80],"especially":[81],"these":[83],"tasks":[84]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
