{"id":"https://openalex.org/W4414041762","doi":"https://doi.org/10.14778/3746405.3746415","title":"Why Are Learned Indexes So Effective but Sometimes Ineffective?","display_name":"Why Are Learned Indexes So Effective but Sometimes Ineffective?","publication_year":2025,"publication_date":"2025-05-01","ids":{"openalex":"https://openalex.org/W4414041762","doi":"https://doi.org/10.14778/3746405.3746415"},"language":"en","primary_location":{"id":"doi:10.14778/3746405.3746415","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3746405.3746415","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"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":"Proceedings of the VLDB Endowment","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/A5046680677","display_name":"Qiyu Liu","orcid":"https://orcid.org/0000-0003-1475-2732"},"institutions":[{"id":"https://openalex.org/I142108993","display_name":"Southwest University","ror":"https://ror.org/01kj4z117","country_code":"CN","type":"education","lineage":["https://openalex.org/I142108993"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiyu Liu","raw_affiliation_strings":["Southwest University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southwest University","institution_ids":["https://openalex.org/I142108993"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Siyuan Han","orcid":null},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Siyuan Han","raw_affiliation_strings":["HKUST"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HKUST","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075950865","display_name":"Yanlin Qi","orcid":"https://orcid.org/0000-0001-6572-1093"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yanlin Qi","raw_affiliation_strings":["HIT Shenzhen"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HIT Shenzhen","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jingshu Peng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jingshu Peng","raw_affiliation_strings":["ByteDance"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077864179","display_name":"Jin Li","orcid":"https://orcid.org/0000-0003-4844-2572"},"institutions":[{"id":"https://openalex.org/I2801851002","display_name":"Harvard University Press","ror":"https://ror.org/006v7bf86","country_code":"US","type":"other","lineage":["https://openalex.org/I136199984","https://openalex.org/I2801851002"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jin Li","raw_affiliation_strings":["Harvard University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harvard University","institution_ids":["https://openalex.org/I2801851002"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101021504","display_name":"Longlong Lin","orcid":"https://orcid.org/0000-0002-2194-8146"},"institutions":[{"id":"https://openalex.org/I142108993","display_name":"Southwest University","ror":"https://ror.org/01kj4z117","country_code":"CN","type":"education","lineage":["https://openalex.org/I142108993"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Longlong Lin","raw_affiliation_strings":["Southwest University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southwest University","institution_ids":["https://openalex.org/I142108993"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100333468","display_name":"Lei Chen","orcid":"https://orcid.org/0000-0002-4279-3892"},"institutions":[{"id":"https://openalex.org/I4210091106","display_name":"Hindustan Petroleum Corporation Limited (India)","ror":"https://ror.org/00axqt112","country_code":"IN","type":"company","lineage":["https://openalex.org/I4210091106"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Lei Chen","raw_affiliation_strings":["HKUST & HKUST (GZ)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HKUST & HKUST (GZ)","institution_ids":["https://openalex.org/I4210091106"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.2763,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.95540848,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":"18","issue":"9","first_page":"2886","last_page":"2898"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9997000098228455,"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":0.9997000098228455,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9980999827384949,"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"}},{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9936000108718872,"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/extension","display_name":"Extension (predicate logic)","score":0.7059000134468079},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6394000053405762},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5911999940872192},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.5382999777793884},{"id":"https://openalex.org/keywords/index","display_name":"Index (typography)","score":0.4603999853134155},{"id":"https://openalex.org/keywords/lookup-table","display_name":"Lookup table","score":0.448199987411499},{"id":"https://openalex.org/keywords/piecewise","display_name":"Piecewise","score":0.44130000472068787}],"concepts":[{"id":"https://openalex.org/C2778029271","wikidata":"https://www.wikidata.org/wiki/Q5421931","display_name":"Extension (predicate logic)","level":2,"score":0.7059000134468079},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6394000053405762},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6389999985694885},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5911999940872192},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5543000102043152},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.5382999777793884},{"id":"https://openalex.org/C2777382242","wikidata":"https://www.wikidata.org/wiki/Q6017816","display_name":"Index (typography)","level":2,"score":0.4603999853134155},{"id":"https://openalex.org/C134835016","wikidata":"https://www.wikidata.org/wiki/Q690265","display_name":"Lookup table","level":2,"score":0.448199987411499},{"id":"https://openalex.org/C164660894","wikidata":"https://www.wikidata.org/wiki/Q2037833","display_name":"Piecewise","level":2,"score":0.44130000472068787},{"id":"https://openalex.org/C17095337","wikidata":"https://www.wikidata.org/wiki/Q2375229","display_name":"Piecewise linear function","level":2,"score":0.42399999499320984},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.3515999913215637},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3375999927520752},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3325999975204468},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.32190001010894775},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3109000027179718},{"id":"https://openalex.org/C2778067643","wikidata":"https://www.wikidata.org/wiki/Q166507","display_name":"Interval (graph theory)","level":2,"score":0.3010999858379364},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.26570001244544983},{"id":"https://openalex.org/C143724316","wikidata":"https://www.wikidata.org/wiki/Q312468","display_name":"Series (stratigraphy)","level":2,"score":0.25949999690055847},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.25270000100135803}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.14778/3746405.3746415","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3746405.3746415","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"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":"Proceedings of the VLDB Endowment","raw_type":"journal-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-168564","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-168564","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W2002555321","https://openalex.org/W2022541337","https://openalex.org/W2033836415","https://openalex.org/W2068739275","https://openalex.org/W2073826297","https://openalex.org/W2124553891","https://openalex.org/W2151224499","https://openalex.org/W2161694911","https://openalex.org/W2167679350","https://openalex.org/W2308827608","https://openalex.org/W2725179571","https://openalex.org/W2799221749","https://openalex.org/W2889524977","https://openalex.org/W2948233700","https://openalex.org/W2979531022","https://openalex.org/W2999149038","https://openalex.org/W3082379938","https://openalex.org/W3096737792","https://openalex.org/W3121516856","https://openalex.org/W3164254023","https://openalex.org/W3173963616","https://openalex.org/W4210819313","https://openalex.org/W4284974261","https://openalex.org/W4294904076","https://openalex.org/W4312637143","https://openalex.org/W4312642611","https://openalex.org/W4372046852","https://openalex.org/W4381621971","https://openalex.org/W4383749424","https://openalex.org/W4399174588","https://openalex.org/W4406628711"],"related_works":["https://openalex.org/W2595172197","https://openalex.org/W2084856301","https://openalex.org/W2127970246","https://openalex.org/W2885125400","https://openalex.org/W1989889224","https://openalex.org/W4382618745","https://openalex.org/W1973775000","https://openalex.org/W2748922771","https://openalex.org/W1987128138","https://openalex.org/W2743976221"],"abstract_inverted_index":{"Learned":[0],"indexes":[1],"have":[2],"attracted":[3],"significant":[4],"research":[5,77],"interest":[6],"due":[7],"to":[8,11,17,51,162,202,208],"their":[9],"potential":[10],"offer":[12],"better":[13],"space-time":[14],"trade-offs":[15],"compared":[16,207],"B+-tree":[18,45],"variants.":[19],"Among":[20],"various":[21],"learned":[22],"indexes,":[23],"the":[24,53,56,61,108,140,147,151,163,209],"PGM-Index":[25,109,165,211],"based":[26],"on":[27],"error-bounded":[28],"piecewise":[29],"linear":[30],"approximation":[31],"is":[32,136],"an":[33],"elegant":[34],"data":[35],"structure":[36],"that":[37,100,133,166],"has":[38],"demonstrated":[39],"provably":[40],"superior":[41],"performance":[42,65,152],"over":[43],"conventional":[44],"indexes.":[46],"However,":[47],"despite":[48],"numerous":[49],"efforts":[50],"optimize":[52],"design":[54],"of":[55,64,104,115,170],"PGM-Index,":[57],"few":[58],"systematically":[59],"study":[60],"root":[62],"causes":[63],"mismatches":[66],"observed":[67],"in":[68,93],"practice.":[69],"In":[70],"this":[71],"paper,":[72],"we":[73,98,131,154],"explore":[74],"two":[75],"key":[76],"questions.":[78],"Q1":[79,96],":":[80,88],"Why":[81,89],"are":[82],"PGM-Indexes":[83,91,135],"theoretically":[84],"effective?":[85],"and":[86,204,212],"Q2":[87,129],"do":[90],"underperform":[92],"practice?":[94],"For":[95,128],",":[97,130],"show":[99,188],"for":[101],"a":[102,112,157,168,179],"set":[103],"N":[105,119,125],"sorted":[106],"keys,":[107],"can":[110],"achieve":[111],"lookup":[113,198],"time":[114],"O":[116,123],"(log":[117],"log":[118],")":[120,126],"while":[121],"using":[122],"(":[124],"space.":[127],"identify":[132],"querying":[134],"highly":[137],"memory-bound,":[138],"where":[139],"internal":[141],"index":[142,197],"search":[143,172],"operations":[144],"often":[145],"become":[146],"bottleneck.":[148],"To":[149],"fill":[150],"gap,":[153],"propose":[155],"PGM++,":[156],"simple":[158],"yet":[159],"effective":[160],"extension":[161],"original":[164,210],"employs":[167],"mixture":[169],"different":[171],"strategies,":[173],"with":[174],"hyper-parameters":[175],"automatically":[176],"tuned":[177],"through":[178],"cost":[180],"model":[181],"calibrated":[182],"by":[183,200],"theoretical":[184],"findings.":[185],"Extensive":[186],"experiments":[187],"that,":[189],"at":[190],"comparable":[191],"space":[192],"costs,":[193],"PGM++":[194],"speeds":[195],"up":[196,201],"queries":[199],"2.31X":[203],"1.56X":[205],"when":[206],"SOTA":[213],"baselines.":[214]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}