{"id":"https://openalex.org/W2965870078","doi":"https://doi.org/10.1145/3292500.3330938","title":"Fast Approximation of Empirical Entropy via Subsampling","display_name":"Fast Approximation of Empirical Entropy via Subsampling","publication_year":2019,"publication_date":"2019-07-25","ids":{"openalex":"https://openalex.org/W2965870078","doi":"https://doi.org/10.1145/3292500.3330938","mag":"2965870078"},"language":"en","primary_location":{"id":"doi:10.1145/3292500.3330938","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3292500.3330938","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","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/A5100342213","display_name":"Chi Wang","orcid":"https://orcid.org/0000-0002-4751-8187"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Chi Wang","raw_affiliation_strings":["Microsoft Research, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090041793","display_name":"Bailu Ding","orcid":"https://orcid.org/0000-0003-4138-6379"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bailu Ding","raw_affiliation_strings":["Microsoft Research, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100342213"],"corresponding_institution_ids":["https://openalex.org/I1290206253"],"apc_list":null,"apc_paid":null,"fwci":0.9801,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.8216901,"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":"658","last_page":"667"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.9987999796867371,"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/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.9987999796867371,"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/T10320","display_name":"Neural Networks and Applications","score":0.9962999820709229,"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/T11106","display_name":"Data Management and Algorithms","score":0.9954000115394592,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/computer-science","display_name":"Computer science","score":0.5845203995704651},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.5749809741973877},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5205515623092651},{"id":"https://openalex.org/keywords/mutual-information","display_name":"Mutual information","score":0.465202659368515},{"id":"https://openalex.org/keywords/approximation-error","display_name":"Approximation error","score":0.4455026686191559},{"id":"https://openalex.org/keywords/bounded-function","display_name":"Bounded function","score":0.44211235642433167},{"id":"https://openalex.org/keywords/approximation-theory","display_name":"Approximation theory","score":0.4324617385864258},{"id":"https://openalex.org/keywords/approximation-algorithm","display_name":"Approximation algorithm","score":0.42462658882141113},{"id":"https://openalex.org/keywords/sample-size-determination","display_name":"Sample size determination","score":0.4171319007873535},{"id":"https://openalex.org/keywords/empirical-research","display_name":"Empirical research","score":0.41256484389305115},{"id":"https://openalex.org/keywords/principle-of-maximum-entropy","display_name":"Principle of maximum entropy","score":0.41052088141441345},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.38910916447639465},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3581447899341583},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.21991166472434998},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2141900658607483}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5845203995704651},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.5749809741973877},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5205515623092651},{"id":"https://openalex.org/C152139883","wikidata":"https://www.wikidata.org/wiki/Q252973","display_name":"Mutual information","level":2,"score":0.465202659368515},{"id":"https://openalex.org/C122383733","wikidata":"https://www.wikidata.org/wiki/Q865920","display_name":"Approximation error","level":2,"score":0.4455026686191559},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.44211235642433167},{"id":"https://openalex.org/C145242015","wikidata":"https://www.wikidata.org/wiki/Q774123","display_name":"Approximation theory","level":2,"score":0.4324617385864258},{"id":"https://openalex.org/C148764684","wikidata":"https://www.wikidata.org/wiki/Q621751","display_name":"Approximation algorithm","level":2,"score":0.42462658882141113},{"id":"https://openalex.org/C129848803","wikidata":"https://www.wikidata.org/wiki/Q2564360","display_name":"Sample size determination","level":2,"score":0.4171319007873535},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.41256484389305115},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.41052088141441345},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.38910916447639465},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3581447899341583},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.21991166472434998},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2141900658607483},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3292500.3330938","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3292500.3330938","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","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":44,"referenced_works":["https://openalex.org/W1512290716","https://openalex.org/W1553290137","https://openalex.org/W1597561788","https://openalex.org/W1656389077","https://openalex.org/W1989151402","https://openalex.org/W2012299525","https://openalex.org/W2032916024","https://openalex.org/W2043772506","https://openalex.org/W2067850927","https://openalex.org/W2078825395","https://openalex.org/W2101985079","https://openalex.org/W2103012681","https://openalex.org/W2103459555","https://openalex.org/W2109885200","https://openalex.org/W2114771311","https://openalex.org/W2118561568","https://openalex.org/W2122943553","https://openalex.org/W2124055802","https://openalex.org/W2127090196","https://openalex.org/W2129501055","https://openalex.org/W2142390772","https://openalex.org/W2149706766","https://openalex.org/W2154053567","https://openalex.org/W2156504490","https://openalex.org/W2293019624","https://openalex.org/W2443837434","https://openalex.org/W2613577383","https://openalex.org/W2742439074","https://openalex.org/W2761580201","https://openalex.org/W2771622871","https://openalex.org/W2808950537","https://openalex.org/W2900925991","https://openalex.org/W2914833637","https://openalex.org/W2963098024","https://openalex.org/W2963430603","https://openalex.org/W2963608890","https://openalex.org/W2989661724","https://openalex.org/W3097993951","https://openalex.org/W3099325309","https://openalex.org/W3103311102","https://openalex.org/W3105524694","https://openalex.org/W4233413206","https://openalex.org/W4241915340","https://openalex.org/W4289236186"],"related_works":["https://openalex.org/W2044115164","https://openalex.org/W2110817230","https://openalex.org/W4308701628","https://openalex.org/W1606488336","https://openalex.org/W2014137052","https://openalex.org/W2165420145","https://openalex.org/W2171221472","https://openalex.org/W1988569331","https://openalex.org/W189995875","https://openalex.org/W3091355678"],"abstract_inverted_index":{"Empirical":[0],"entropy":[1,6,43,63],"refers":[2],"to":[3,86,113,148],"the":[4,9,28,40,61,71,74,87,99,116,129],"information":[5],"calculated":[7],"from":[8,98],"empirical":[10,42,62,137],"distribution":[11],"of":[12,30,60,128,133,139,151],"a":[13,17,45,52,79],"dataset.":[14],"It":[15],"is":[16,131],"widely":[18],"used":[19],"aggregation":[20,32],"function":[21],"for":[22,70],"knowledge":[23],"discovery,":[24],"as":[25,27,35],"well":[26],"foundation":[29],"other":[31],"functions":[33],"such":[34],"mutual":[36,108],"information.":[37,109],"However,":[38],"computing":[39],"exact":[41,155],"on":[44,107,142],"large-scale":[46,143],"dataset":[47,117],"can":[48,56,96],"be":[49],"expensive.":[50],"Using":[51],"random":[53],"subsample,":[54],"we":[55],"compute":[57],"an":[58],"approximation":[59],"efficiently.":[64],"We":[65,90,110],"derive":[66],"probabilistic":[67],"error":[68,75],"bounds":[69,76],"approximation,":[72],"where":[73],"reduce":[77],"in":[78],"near":[80],"square":[81],"root":[82],"rate":[83],"with":[84,122,157],"respect":[85],"subsample":[88,115],"size.":[89,135],"further":[91],"study":[92],"two":[93],"applications":[94],"which":[95],"benefit":[97],"error-bounded":[100],"approximation:":[101],"feature":[102],"ranking":[103],"and":[104,118],"filtering":[105],"based":[106],"develop":[111],"algorithms":[112,130,141],"progressively":[114],"return":[119],"correct":[120],"answers":[121],"high":[123],"probability.":[124],"The":[125,136],"sample":[126],"complexity":[127],"independent":[132],"data":[134],"evaluation":[138],"our":[140],"real-world":[144],"datasets":[145],"demonstrates":[146],"up":[147],"three":[149],"orders":[150],"magnitude":[152],"speedup":[153],"over":[154],"methods":[156],"\\errrate\\":[158],"error.":[159]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}