{"id":"https://openalex.org/W2124055802","doi":null,"title":"Estimating the Unseen: Improved Estimators for Entropy and other Properties","display_name":"Estimating the Unseen: Improved Estimators for Entropy and other Properties","publication_year":2013,"publication_date":"2013-12-05","ids":{"openalex":"https://openalex.org/W2124055802","mag":"2124055802"},"language":"en","primary_location":{"id":"mag:2124055802","doi":null,"is_oa":false,"landing_page_url":"https://papers.nips.cc/paper/2013/file/53c04118df112c13a8c34b38343b9c10-Paper.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Neural Information Processing Systems","raw_type":null},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"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/A5036230157","display_name":"Paul Valiant","orcid":"https://orcid.org/0000-0001-5523-2974","observed_orcids":["https://orcid.org/0000-0001-5523-2974"]},"institutions":[{"id":"https://openalex.org/I27804330","display_name":"Brown University","ror":"https://ror.org/05gq02987","country_code":"US","type":"education","lineage":["https://openalex.org/I27804330"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Paul Valiant","raw_affiliation_strings":["Brown University, Providence, RI,"],"raw_orcid":"https://orcid.org/0000-0001-5523-2974","affiliations":[{"raw_affiliation_string":"Brown University, Providence, RI,","institution_ids":["https://openalex.org/I27804330"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079503799","display_name":"Gregory J. Valiant","orcid":"https://orcid.org/0000-0002-2211-1073","observed_orcids":["https://orcid.org/0000-0002-2211-1073"]},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gregory Valiant","raw_affiliation_strings":["Stanford University Stanford CA"],"raw_orcid":"https://orcid.org/0000-0002-2211-1073","affiliations":[{"raw_affiliation_string":"Stanford University Stanford CA","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.319,"has_fulltext":false,"cited_by_count":83,"citation_normalized_percentile":{"value":0.97053986,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":99},"biblio":{"volume":"26","issue":null,"first_page":"2157","last_page":"2165"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13500","display_name":"Probability and Statistical Research","score":0.3668999969959259,"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"}},"topics":[{"id":"https://openalex.org/T13500","display_name":"Probability and Statistical Research","score":0.3668999969959259,"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"}},{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.09359999746084213,"subfield":{"id":"https://openalex.org/subfields/2614","display_name":"Theoretical Computer Science"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10136","display_name":"Statistical Methods and Inference","score":0.03269999846816063,"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/entropy-estimation","display_name":"entropy estimation","score":0.7889999747276306},{"id":"https://openalex.org/keywords/distributional-properties","display_name":"distributional properties","score":0.7239999771118164},{"id":"https://openalex.org/keywords/distribution-distance","display_name":"distance between distributions","score":0.7099999785423279},{"id":"https://openalex.org/keywords/property-testing","display_name":"property testing","score":0.45899999141693115},{"id":"https://openalex.org/keywords/estimator-optimality","display_name":"estimator optimality","score":0.6669999957084656}],"concepts":[{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.748079776763916},{"id":"https://openalex.org/C117160843","wikidata":"https://www.wikidata.org/wiki/Q338652","display_name":"Sublinear function","level":2,"score":0.6208470463752747},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.5548537373542786},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5425620079040527},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.47950488328933716},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.4620148241519928},{"id":"https://openalex.org/C2777027219","wikidata":"https://www.wikidata.org/wiki/Q1284190","display_name":"Constant (computer programming)","level":2,"score":0.45773011445999146},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4486553370952606},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.4414888918399811},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.42995941638946533},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.30076783895492554},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2780722379684448},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.1028003990650177},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:2124055802","doi":null,"is_oa":false,"landing_page_url":"https://papers.nips.cc/paper/2013/file/53c04118df112c13a8c34b38343b9c10-Paper.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Neural Information Processing Systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W226098375","https://openalex.org/W1585701772","https://openalex.org/W1595687138","https://openalex.org/W1873671735","https://openalex.org/W1947089506","https://openalex.org/W1971405816","https://openalex.org/W1982516282","https://openalex.org/W1982918157","https://openalex.org/W1987754412","https://openalex.org/W1988624553","https://openalex.org/W1992068214","https://openalex.org/W2022257958","https://openalex.org/W2058991275","https://openalex.org/W2069241007","https://openalex.org/W2082092506","https://openalex.org/W2094608047","https://openalex.org/W2097580994","https://openalex.org/W2114771311","https://openalex.org/W2127090196","https://openalex.org/W2134169350","https://openalex.org/W2135827220","https://openalex.org/W2146368895","https://openalex.org/W2187447858","https://openalex.org/W2510474575","https://openalex.org/W4233471163","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2762763087","https://openalex.org/W1553031635","https://openalex.org/W7097395480","https://openalex.org/W7097862756","https://openalex.org/W2920524057","https://openalex.org/W7097031912","https://openalex.org/W1982918157","https://openalex.org/W2002561524","https://openalex.org/W2890291628","https://openalex.org/W2948032643"],"abstract_inverted_index":{"Recently,":[0],"Valiant":[1,3],"and":[2,26,79,93,183,201],"[1,":[4],"2]":[5],"showed":[6],"that":[7,188],"a":[8,37,43,65,73,102,108,114,195],"class":[9],"of":[10,23,31,46,67,76,104,110,117,138,158,162,171,175],"distributional":[11],"properties,":[12],"which":[13,152],"includes":[14],"such":[15,144],"practically":[16],"relevant":[17],"properties":[18,59],"as":[19,146,194],"entropy,":[20],"the":[21,121,131,135,139,147,154,159,163,169,172,176],"number":[22],"distinct":[24,56],"elements,":[25,57],"distance":[27],"metrics":[28],"between":[29],"pairs":[30],"distributions,":[32,112],"can":[33,60],"be":[34,61,191],"estimated":[35,62],"given":[36,42],"sublinear":[38],"sized":[39],"sample.":[40],"Specifically,":[41],"sample":[44,66,132],"consisting":[45],"independent":[47],"draws":[48],"from":[49],"any":[50],"distribution":[51],"over":[52,90],"at":[53],"most":[54],"n":[55],"these":[58],"accurately":[63],"using":[64],"size":[68],"O(n/":[69],"log":[70],"n).We":[71],"propose":[72],"novel":[74],"modification":[75],"this":[77,83],"approach":[78,126,179],"show:":[80],"1)":[81],"theoretically,":[82],"estimator":[84],"is":[85,127,180],"optimal":[86],"(to":[87],"constant":[88],"factors,":[89],"worst-case":[91],"instances),":[92],"2)":[94],"in":[95,124],"practice,":[96],"it":[97,189],"performs":[98],"exceptionally":[99],"well":[100],"for":[101,113],"variety":[103,109],"estimation":[105,150],"tasks,":[106],"on":[107],"natural":[111],"wide":[115],"range":[116],"parameters.":[118],"Perhaps":[119],"unsurprisingly,":[120],"key":[122],"step":[123],"our":[125],"to":[128,133,167],"first":[129],"use":[130],"characterize":[134],"unseen":[136],"portion":[137,161,174],"distribution.":[140,177],"This":[141,178],"goes":[142],"beyond":[143],"tools":[145],"Good-Turing":[148],"frequency":[149],"scheme,":[151],"estimates":[153],"total":[155],"probability":[156],"mass":[157],"unobserved":[160,173],"distribution:":[164],"we":[165,186],"seek":[166],"estimate":[168],"shape":[170],"robust,":[181],"general,":[182],"theoretically":[184],"principled;":[185],"expect":[187],"may":[190],"fruitfully":[192],"used":[193],"component":[196],"within":[197],"larger":[198],"machine":[199],"learning":[200],"data":[202],"analysis":[203],"systems.":[204]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":13},{"year":2019,"cited_by_count":14},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":11},{"year":2016,"cited_by_count":9},{"year":2015,"cited_by_count":9},{"year":2014,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2016-06-24T00:00:00"}