{"id":"https://openalex.org/W2043160138","doi":"https://doi.org/10.1145/1597036.1597038","title":"Sublinear estimation of entropy and information distances","display_name":"Sublinear estimation of entropy and information distances","publication_year":2009,"publication_date":"2009-10-01","ids":{"openalex":"https://openalex.org/W2043160138","doi":"https://doi.org/10.1145/1597036.1597038","mag":"2043160138"},"language":"en","primary_location":{"id":"doi:10.1145/1597036.1597038","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1597036.1597038","pdf_url":null,"source":{"id":"https://openalex.org/S137348503","display_name":"ACM Transactions on Algorithms","issn_l":"1549-6325","issn":["1549-6325","1549-6333"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Algorithms","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/A5114008024","display_name":"Sudipto Guha","orcid":null},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Sudipto Guha","raw_affiliation_strings":["University of Pennsylvania, Philadelphia, PA"],"affiliations":[{"raw_affiliation_string":"University of Pennsylvania, Philadelphia, PA","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101979548","display_name":"Andrew McGregor","orcid":"https://orcid.org/0000-0002-2124-160X"},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew McGregor","raw_affiliation_strings":["University of Massachusetts, Amherst, MA"],"affiliations":[{"raw_affiliation_string":"University of Massachusetts, Amherst, MA","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061790878","display_name":"Suresh Venkatasubramanian","orcid":"https://orcid.org/0000-0001-7679-7130"},"institutions":[{"id":"https://openalex.org/I223532165","display_name":"University of Utah","ror":"https://ror.org/03r0ha626","country_code":"US","type":"education","lineage":["https://openalex.org/I223532165"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Suresh Venkatasubramanian","raw_affiliation_strings":["University of Utah, Salt Lake City, UT","University of Utah; Salt Lake City; UT"],"affiliations":[{"raw_affiliation_string":"University of Utah, Salt Lake City, UT","institution_ids":["https://openalex.org/I223532165"]},{"raw_affiliation_string":"University of Utah; Salt Lake City; UT","institution_ids":["https://openalex.org/I223532165"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5114008024"],"corresponding_institution_ids":["https://openalex.org/I79576946"],"apc_list":null,"apc_paid":null,"fwci":2.2525,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.89285784,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"5","issue":"4","first_page":"1","last_page":"16"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.9987000226974487,"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":0.9987000226974487,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.995199978351593,"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/T12002","display_name":"Computability, Logic, AI Algorithms","score":0.9918000102043152,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/sublinear-function","display_name":"Sublinear function","score":0.8277696967124939},{"id":"https://openalex.org/keywords/oracle","display_name":"Oracle","score":0.6276960372924805},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.5373553037643433},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5021586418151855},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.47420433163642883},{"id":"https://openalex.org/keywords/hellinger-distance","display_name":"Hellinger distance","score":0.42604804039001465},{"id":"https://openalex.org/keywords/data-stream-mining","display_name":"Data stream mining","score":0.4223615527153015},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.37376466393470764},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3602791130542755},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.28148144483566284},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.21413755416870117},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.17612501978874207}],"concepts":[{"id":"https://openalex.org/C117160843","wikidata":"https://www.wikidata.org/wiki/Q338652","display_name":"Sublinear function","level":2,"score":0.8277696967124939},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.6276960372924805},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.5373553037643433},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5021586418151855},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.47420433163642883},{"id":"https://openalex.org/C153024298","wikidata":"https://www.wikidata.org/wiki/Q3030678","display_name":"Hellinger distance","level":2,"score":0.42604804039001465},{"id":"https://openalex.org/C89198739","wikidata":"https://www.wikidata.org/wiki/Q3079880","display_name":"Data stream mining","level":2,"score":0.4223615527153015},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.37376466393470764},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3602791130542755},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.28148144483566284},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.21413755416870117},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.17612501978874207},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1597036.1597038","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1597036.1597038","pdf_url":null,"source":{"id":"https://openalex.org/S137348503","display_name":"ACM Transactions on Algorithms","issn_l":"1549-6325","issn":["1549-6325","1549-6333"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Algorithms","raw_type":"journal-article"},{"id":"pmh:oai:scholarworks.umass.edu:cs_faculty_pubs-1911","is_oa":false,"landing_page_url":"https://scholarworks.umass.edu/cs_faculty_pubs/912","pdf_url":null,"source":{"id":"https://openalex.org/S4306402057","display_name":"Scholarworks (University of Massachusetts Amherst)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I24603500","host_organization_name":"University of Massachusetts Amherst","host_organization_lineage":["https://openalex.org/I24603500"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Computer Science Department Faculty Publication Series","raw_type":"text"},{"id":"pmh:oai:scholarworks.umass.edu:20.500.14394/10499","is_oa":false,"landing_page_url":"https://hdl.handle.net/20.500.14394/10499","pdf_url":null,"source":{"id":"https://openalex.org/S4306402240","display_name":"ScholarWorks@UMassAmherst (University of Massachusetts Amherst)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I24603500","host_organization_name":"University of Massachusetts Amherst","host_organization_lineage":["https://openalex.org/I24603500"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"published","raw_type":"Article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3077210781","display_name":null,"funder_award_id":"N00014-04-1-0735","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G8095836194","display_name":null,"funder_award_id":"CCF-0430376","funder_id":"https://openalex.org/F4320337387","funder_display_name":"Division of Computing and Communication Foundations"}],"funders":[{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"},{"id":"https://openalex.org/F4320337387","display_name":"Division of Computing and Communication Foundations","ror":"https://ror.org/01mng8331"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W69989483","https://openalex.org/W107085514","https://openalex.org/W152055444","https://openalex.org/W201917955","https://openalex.org/W638747377","https://openalex.org/W1484190527","https://openalex.org/W1489843519","https://openalex.org/W1520168181","https://openalex.org/W1533319289","https://openalex.org/W1558846832","https://openalex.org/W1603123426","https://openalex.org/W1628908379","https://openalex.org/W1675727887","https://openalex.org/W1761167196","https://openalex.org/W1983266860","https://openalex.org/W1988624553","https://openalex.org/W1995875735","https://openalex.org/W2076381458","https://openalex.org/W2078764670","https://openalex.org/W2080745194","https://openalex.org/W2085533912","https://openalex.org/W2095374884","https://openalex.org/W2096765209","https://openalex.org/W2099111195","https://openalex.org/W2103174987","https://openalex.org/W2106163100","https://openalex.org/W2109885200","https://openalex.org/W2113061123","https://openalex.org/W2116336583","https://openalex.org/W2130598205","https://openalex.org/W2134169350","https://openalex.org/W2138570191","https://openalex.org/W2155969596","https://openalex.org/W2159902206","https://openalex.org/W2163964823","https://openalex.org/W2621193479","https://openalex.org/W2915011089","https://openalex.org/W2979454998","https://openalex.org/W4241915340"],"related_works":["https://openalex.org/W2388505395","https://openalex.org/W2055900741","https://openalex.org/W1766698920","https://openalex.org/W3199206686","https://openalex.org/W2583943427","https://openalex.org/W2392953011","https://openalex.org/W3001055881","https://openalex.org/W2938185404","https://openalex.org/W2043160138","https://openalex.org/W1956699040"],"abstract_inverted_index":{"In":[0,131,196],"many":[1],"data":[2,9,123,232],"mining":[3],"and":[4,52,165,211],"machine":[5],"learning":[6],"problems,":[7],"the":[8,50,59,85,119,122,173,193,197,204,207,212,228],"items":[10],"that":[11,29,127,176,234],"need":[12,93],"to":[13,94,101,227],"be":[14,102],"clustered":[15],"or":[16],"classified":[17],"are":[18,27,40,64,88,147,235,243],"not":[19,41],"arbitrary":[20],"points":[21,31],"in":[22,79,99,104,113,117,149,192],"a":[23,33,62,76,108,135,168],"high-dimensional":[24,34],"space,":[25],"but":[26,45],"distributions,":[28,37],"is,":[30],"on":[32,142],"simplex.":[35],"For":[36],"natural":[38,66],"measures":[39,47],"\u2113":[42],"p":[43],"distances,":[44],"information-theoretic":[46,151],"such":[48,57],"as":[49,58],"Kullback-Leibler":[51],"Hellinger":[53],"divergences.":[54],"Similarly,":[55],"quantities":[56,74,191],"entropy":[60,166],"of":[61,72,110,199],"distribution":[63],"more":[65,169],"than":[67,239],"frequency":[68],"moments.":[69],"Efficient":[70],"estimation":[71],"these":[73,91,190],"is":[75,230],"key":[77],"component":[78,226],"algorithms":[80,92,112,160,188],"for":[81,161,189],"manipulating":[82],"distributions.":[83],"Since":[84],"datasets":[86],"involved":[87],"typically":[89],"massive,":[90],"have":[95],"only":[96],"sublinear":[97],"complexity":[98],"order":[100],"feasible":[103],"practice.":[105],"We":[106,156],"present":[107,158],"range":[109],"sublinear-time":[111],"various":[114,129,163],"oracle":[115,126,171,175,209],"models":[116,210],"which":[118,242],"algorithm":[120],"accesses":[121],"via":[124],"an":[125,150],"supports":[128],"queries.":[130],"particular,":[132],"we":[133,185,202],"answer":[134],"question":[136],"posed":[137],"by":[138,180,219],"Batu":[139,181],"et":[140,182,221],"al.":[141,183,222],"testing":[143],"whether":[144],"two":[145],"distributions":[146],"close":[148],"sense":[152],"given":[153],"independent":[154],"samples.":[155],"then":[157],"optimal":[159],"estimating":[162],"information-divergences":[164],"with":[167],"powerful":[170],"called":[172],"combined":[174],"was":[177],"also":[178],"considered":[179],"Finally,":[184],"consider":[186],"sublinear-space":[187],"data-stream":[194,213],"model.":[195,214],"course":[198],"doing":[200],"so,":[201],"explore":[203],"relationship":[205],"between":[206],"aforementioned":[208],"This":[215],"continues":[216],"work":[217],"initiated":[218],"Feigenbaum":[220],"An":[223],"important":[224],"additional":[225],"study":[229],"considering":[231],"streams":[233],"ordered":[236,244],"randomly":[237],"rather":[238],"just":[240],"those":[241],"adversarially.":[245]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":4}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}