{"id":"https://openalex.org/W3034984817","doi":"https://doi.org/10.24963/ijcai.2020/389","title":"Mutual Information Estimation using LSH Sampling","display_name":"Mutual Information Estimation using LSH Sampling","publication_year":2020,"publication_date":"2020-07-01","ids":{"openalex":"https://openalex.org/W3034984817","doi":"https://doi.org/10.24963/ijcai.2020/389","mag":"3034984817"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2020/389","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/389","pdf_url":"https://www.ijcai.org/proceedings/2020/0389.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2020/0389.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5013062640","display_name":"Ryan Spring","orcid":"https://orcid.org/0000-0001-9166-0079"},"institutions":[{"id":"https://openalex.org/I74775410","display_name":"Rice University","ror":"https://ror.org/008zs3103","country_code":"US","type":"education","lineage":["https://openalex.org/I74775410"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ryan Spring","raw_affiliation_strings":["Rice University","Rice University, Houston, Texas, USA"],"affiliations":[{"raw_affiliation_string":"Rice University","institution_ids":["https://openalex.org/I74775410"]},{"raw_affiliation_string":"Rice University, Houston, Texas, USA","institution_ids":["https://openalex.org/I74775410"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024993683","display_name":"Anshumali Shrivastava","orcid":"https://orcid.org/0000-0002-5042-2856"},"institutions":[{"id":"https://openalex.org/I74775410","display_name":"Rice University","ror":"https://ror.org/008zs3103","country_code":"US","type":"education","lineage":["https://openalex.org/I74775410"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anshumali Shrivastava","raw_affiliation_strings":["Rice University","Rice University, Houston, Texas, USA"],"affiliations":[{"raw_affiliation_string":"Rice University","institution_ids":["https://openalex.org/I74775410"]},{"raw_affiliation_string":"Rice University, Houston, Texas, USA","institution_ids":["https://openalex.org/I74775410"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5013062640"],"corresponding_institution_ids":["https://openalex.org/I74775410"],"apc_list":null,"apc_paid":null,"fwci":0.6797,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.76445613,"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":"2807","last_page":"2815"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9988999962806702,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9988999962806702,"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":0.9970999956130981,"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/T12879","display_name":"Distributed Sensor Networks and Detection Algorithms","score":0.9922000169754028,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.6697956323623657},{"id":"https://openalex.org/keywords/mutual-information","display_name":"Mutual information","score":0.6382629871368408},{"id":"https://openalex.org/keywords/upper-and-lower-bounds","display_name":"Upper and lower bounds","score":0.6084586381912231},{"id":"https://openalex.org/keywords/locality-sensitive-hashing","display_name":"Locality-sensitive hashing","score":0.5035125613212585},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.4984872341156006},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4904308021068573},{"id":"https://openalex.org/keywords/bounded-function","display_name":"Bounded function","score":0.47377562522888184},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.4652382433414459},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.4519517123699188},{"id":"https://openalex.org/keywords/bias-of-an-estimator","display_name":"Bias of an estimator","score":0.4434019923210144},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.40791189670562744},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.40397435426712036},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.373765766620636},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.36647170782089233},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3608061671257019},{"id":"https://openalex.org/keywords/minimum-variance-unbiased-estimator","display_name":"Minimum-variance unbiased estimator","score":0.3145639896392822},{"id":"https://openalex.org/keywords/hash-table","display_name":"Hash table","score":0.13972792029380798}],"concepts":[{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.6697956323623657},{"id":"https://openalex.org/C152139883","wikidata":"https://www.wikidata.org/wiki/Q252973","display_name":"Mutual information","level":2,"score":0.6382629871368408},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.6084586381912231},{"id":"https://openalex.org/C74270461","wikidata":"https://www.wikidata.org/wiki/Q1625299","display_name":"Locality-sensitive hashing","level":4,"score":0.5035125613212585},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.4984872341156006},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4904308021068573},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.47377562522888184},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.4652382433414459},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.4519517123699188},{"id":"https://openalex.org/C191393472","wikidata":"https://www.wikidata.org/wiki/Q15222032","display_name":"Bias of an estimator","level":4,"score":0.4434019923210144},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.40791189670562744},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.40397435426712036},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.373765766620636},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.36647170782089233},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3608061671257019},{"id":"https://openalex.org/C165646398","wikidata":"https://www.wikidata.org/wiki/Q3755281","display_name":"Minimum-variance unbiased estimator","level":3,"score":0.3145639896392822},{"id":"https://openalex.org/C67388219","wikidata":"https://www.wikidata.org/wiki/Q207440","display_name":"Hash table","level":3,"score":0.13972792029380798},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"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:10.24963/ijcai.2020/389","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/389","pdf_url":"https://www.ijcai.org/proceedings/2020/0389.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2020/389","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/389","pdf_url":"https://www.ijcai.org/proceedings/2020/0389.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1523888516","display_name":null,"funder_award_id":"FA9550-","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"},{"id":"https://openalex.org/G2344778886","display_name":"BIGDATA: F:  Collaborative Research: Theory and Practice of Randomized Algorithms for Ultra-Large-Scale Signal Processing","funder_award_id":"1838177","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3666695478","display_name":null,"funder_award_id":"BIGDATA","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3673415204","display_name":null,"funder_award_id":"FA9550-18-1-01","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"},{"id":"https://openalex.org/G5809100787","display_name":null,"funder_award_id":"FA9550","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"},{"id":"https://openalex.org/G6098521345","display_name":null,"funder_award_id":"FA9550","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G7026865386","display_name":null,"funder_award_id":"FA9550-18-1-0152","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"},{"id":"https://openalex.org/G8144157170","display_name":null,"funder_award_id":"FA9550-18-1-015","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"},{"id":"https://openalex.org/F4320338279","display_name":"Air Force Office of Scientific Research","ror":"https://ror.org/011e9bt93"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3034984817.pdf","grobid_xml":"https://content.openalex.org/works/W3034984817.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W1502916507","https://openalex.org/W1736726159","https://openalex.org/W2012833704","https://openalex.org/W2108384452","https://openalex.org/W2122925692","https://openalex.org/W2131929066","https://openalex.org/W2152790380","https://openalex.org/W2166944917","https://openalex.org/W2279057335","https://openalex.org/W2408128689","https://openalex.org/W2609517418","https://openalex.org/W2735292373","https://openalex.org/W2788362551","https://openalex.org/W2887997457","https://openalex.org/W2896457183","https://openalex.org/W2948012107","https://openalex.org/W2949759968","https://openalex.org/W2963341956","https://openalex.org/W2963677907","https://openalex.org/W2970617576","https://openalex.org/W2971155163","https://openalex.org/W3012839000","https://openalex.org/W4230940751","https://openalex.org/W4297808394","https://openalex.org/W4300060681","https://openalex.org/W4300601563","https://openalex.org/W4300636703"],"related_works":["https://openalex.org/W2349547417","https://openalex.org/W4237435333","https://openalex.org/W4210503132","https://openalex.org/W2999390738","https://openalex.org/W2352602506","https://openalex.org/W3092888124","https://openalex.org/W2093865141","https://openalex.org/W4239491110","https://openalex.org/W2368191880","https://openalex.org/W2910434125"],"abstract_inverted_index":{"Learning":[0],"representations":[1],"in":[2,16,154],"an":[3,70,140,145],"unsupervised":[4],"or":[5],"self-supervised":[6],"manner":[7],"is":[8,43,58,64,93,99,168],"a":[9,88,181],"growing":[10],"area":[11],"of":[12,33,67,91,118],"research.":[13],"Current":[14],"approaches":[15],"representation":[17,28],"learning":[18],"seek":[19],"to":[20,38,79,100,187],"maximize":[21],"the":[22,26,34,65,76,81,102,105,109,115,119,124,151,165],"mutual":[23,40],"information":[24,41],"between":[25],"learned":[27],"and":[29,143,162],"original":[30],"data.":[31],"One":[32],"most":[35,82],"popular":[36],"ways":[37],"estimate":[39,52,107,114,179],"(MI)":[42],"based":[44],"on":[45],"Noise":[46],"Contrastive":[47],"Estimation":[48],"(NCE).":[49],"This":[50],"MI":[51,106],"exhibits":[53],"low":[54],"variance,":[55],"but":[56,164],"it":[57],"upper-bounded":[59],"by":[60],"log(N),":[61],"where":[62],"N":[63],"number":[66,90],"samples.":[68],"In":[69,131],"ideal":[71],"scenario,":[72],"we":[73,113,134],"would":[74],"use":[75,135],"entire":[77,125],"dataset":[78,126],"get":[80],"accurate":[83],"estimate.":[84],"However,":[85],"using":[86,127],"such":[87],"large":[89],"samples":[92,159],"computationally":[94],"prohibitive.":[95],"Our":[96],"proposed":[97],"solution":[98],"decouple":[101],"upper-bound":[103],"for":[104,123],"from":[108],"sample":[110],"size.":[111],"Instead,":[112],"partition":[116,152],"function":[117,122,153],"NCE":[120],"loss":[121],"importance":[128],"sampling":[129,178],"(IS).":[130],"this":[132],"paper,":[133],"locality-sensitive":[136],"hashing":[137],"(LSH)":[138],"as":[139],"adaptive":[141],"sampler":[142],"propose":[144],"unbiased":[146,169],"estimator":[147,167],"that":[148,175],"accurately":[149],"approximates":[150],"sub-linear":[155],"(near-constant)":[156],"time.":[157],"The":[158],"are":[160],"correlated":[161],"non-normalized,":[163],"derived":[166],"without":[170],"any":[171],"assumptions.":[172],"We":[173],"show":[174],"our":[176],"LSH":[177],"provides":[180],"superior":[182],"bias-variance":[183],"trade-off":[184],"when":[185],"compared":[186],"other":[188],"state-of-the-art":[189],"approaches.":[190]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}