{"id":"https://openalex.org/W7138915493","doi":"https://doi.org/10.1145/3802002","title":"100x Cost & Latency Reduction: Performance Analysis of AI Query Approximation using Lightweight Proxy Models: [Experiments & Analysis]","display_name":"100x Cost & Latency Reduction: Performance Analysis of AI Query Approximation using Lightweight Proxy Models: [Experiments & Analysis]","publication_year":2026,"publication_date":"2026-05-18","ids":{"openalex":"https://openalex.org/W7138915493","doi":"https://doi.org/10.1145/3802002"},"language":"en","primary_location":{"id":"doi:10.1145/3802002","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3802002","pdf_url":null,"source":{"id":"https://openalex.org/S4387289859","display_name":"Proceedings of the ACM on Management of Data","issn_l":"2836-6573","issn":["2836-6573"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Management of Data","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1145/3802002","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5087758743","display_name":"Yeounoh Chung","orcid":"https://orcid.org/0000-0002-6535-9001"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yeounoh Chung","raw_affiliation_strings":["Google Cloud, Sunnyvale, USA"],"raw_orcid":"https://orcid.org/0009-0004-3947-2782","affiliations":[{"raw_affiliation_string":"Google Cloud, Sunnyvale, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5098770155","display_name":"Rushabh Desai","orcid":"https://orcid.org/0009-0001-7406-8433"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rushabh Desai","raw_affiliation_strings":["Google Cloud, Seattle, USA"],"raw_orcid":"https://orcid.org/0009-0001-7406-8433","affiliations":[{"raw_affiliation_string":"Google Cloud, Seattle, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130101607","display_name":"Jian He","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jian He","raw_affiliation_strings":["Google Cloud, Seattle, USA"],"raw_orcid":"https://orcid.org/0009-0000-5088-4308","affiliations":[{"raw_affiliation_string":"Google Cloud, Seattle, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130048852","display_name":"Yu Xiao","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yu Xiao","raw_affiliation_strings":["Google Cloud, Seattle, USA"],"raw_orcid":"https://orcid.org/0009-0008-4837-151X","affiliations":[{"raw_affiliation_string":"Google Cloud, Seattle, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130016301","display_name":"Thibaud Hottelier","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Thibaud Hottelier","raw_affiliation_strings":["Google Cloud, Seattle, USA"],"raw_orcid":"https://orcid.org/0009-0008-4491-2227","affiliations":[{"raw_affiliation_string":"Google Cloud, Seattle, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073194788","display_name":"Yves-Laurent Kom Samo","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yves-Laurent Kom Samo","raw_affiliation_strings":["Google Cloud, Seattle, USA"],"raw_orcid":"https://orcid.org/0000-0003-2901-6930","affiliations":[{"raw_affiliation_string":"Google Cloud, Seattle, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027527327","display_name":"Pushkar Khadilkar","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pushkar Khadilkar","raw_affiliation_strings":["Google Cloud, Pune, India"],"raw_orcid":"https://orcid.org/0009-0008-6625-1423","affiliations":[{"raw_affiliation_string":"Google Cloud, Pune, India","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129756843","display_name":"Xianshun Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xianshun Chen","raw_affiliation_strings":["Google Cloud, Seattle, USA"],"raw_orcid":"https://orcid.org/0009-0001-7659-7152","affiliations":[{"raw_affiliation_string":"Google Cloud, Seattle, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040126908","display_name":"Sam Idicula","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sam Idicula","raw_affiliation_strings":["Google Cloud, Sunnyvale, USA"],"raw_orcid":"https://orcid.org/0009-0009-4562-0557","affiliations":[{"raw_affiliation_string":"Google Cloud, Sunnyvale, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129954134","display_name":"Fatma \u00d6zcan","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fatma Ozcan","raw_affiliation_strings":["Google Cloud, Sunnyvale, USA"],"raw_orcid":"https://orcid.org/0000-0002-4418-4724","affiliations":[{"raw_affiliation_string":"Google Cloud, Sunnyvale, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067621853","display_name":"Alon Halevy","orcid":"https://orcid.org/0000-0002-8717-7356"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alon Halevy","raw_affiliation_strings":["Google Cloud, Sunnyvale, USA"],"raw_orcid":"https://orcid.org/0000-0002-8717-7356","affiliations":[{"raw_affiliation_string":"Google Cloud, Sunnyvale, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059167302","display_name":"Yannis Papakonstantinou","orcid":"https://orcid.org/0009-0007-6360-9496"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yannis Papakonstantinou","raw_affiliation_strings":["Google Cloud, Sunnyvale, USA"],"raw_orcid":"https://orcid.org/0009-0007-6360-9496","affiliations":[{"raw_affiliation_string":"Google Cloud, Sunnyvale, USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.29308262,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"4","issue":"3","first_page":"1","last_page":"23"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.4927000105381012,"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"}},"topics":[{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.4927000105381012,"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/T11719","display_name":"Data Quality and Management","score":0.323199987411499,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.033799998462200165,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/proxy","display_name":"Proxy (statistics)","score":0.6414999961853027},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5478000044822693},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.5220999717712402},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.5055999755859375},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.4650000035762787},{"id":"https://openalex.org/keywords/sql","display_name":"SQL","score":0.4609000086784363},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.4296000003814697},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.37790000438690186},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.3571000099182129}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8618999719619751},{"id":"https://openalex.org/C2780148112","wikidata":"https://www.wikidata.org/wiki/Q1432581","display_name":"Proxy (statistics)","level":2,"score":0.6414999961853027},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5478000044822693},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.5220999717712402},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5055999755859375},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.4650000035762787},{"id":"https://openalex.org/C510870499","wikidata":"https://www.wikidata.org/wiki/Q47607","display_name":"SQL","level":2,"score":0.4609000086784363},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4296000003814697},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.42399999499320984},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.37790000438690186},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.3571000099182129},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.35260000824928284},{"id":"https://openalex.org/C2781252014","wikidata":"https://www.wikidata.org/wiki/Q1141900","display_name":"Unstructured data","level":3,"score":0.32010000944137573},{"id":"https://openalex.org/C17305859","wikidata":"https://www.wikidata.org/wiki/Q382944","display_name":"Soar","level":2,"score":0.3172999918460846},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.3163999915122986},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.31029999256134033},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.3052000105381012},{"id":"https://openalex.org/C148764684","wikidata":"https://www.wikidata.org/wiki/Q621751","display_name":"Approximation algorithm","level":2,"score":0.30149999260902405},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3010999858379364},{"id":"https://openalex.org/C47487241","wikidata":"https://www.wikidata.org/wiki/Q5227230","display_name":"Data access","level":2,"score":0.27219998836517334},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.27140000462532043},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.26739999651908875},{"id":"https://openalex.org/C2779298391","wikidata":"https://www.wikidata.org/wiki/Q11189","display_name":"Proxy server","level":2,"score":0.26420000195503235},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2639999985694885},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.2535000145435333}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3802002","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3802002","pdf_url":null,"source":{"id":"https://openalex.org/S4387289859","display_name":"Proceedings of the ACM on Management of Data","issn_l":"2836-6573","issn":["2836-6573"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Management of Data","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2603.15970","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2603.15970","pdf_url":"https://arxiv.org/pdf/2603.15970","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"}],"best_oa_location":{"id":"doi:10.1145/3802002","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3802002","pdf_url":null,"source":{"id":"https://openalex.org/S4387289859","display_name":"Proceedings of the ACM on Management of Data","issn_l":"2836-6573","issn":["2836-6573"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Management of Data","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Several":[0],"data":[1],"warehouse":[2],"and":[3,20,44,60,66,102,115,124,134,141,157,164,199],"database":[4,103],"providers":[5],"have":[6],"recently":[7],"introduced":[8],"extensions":[9],"to":[10,17,105],"SQL":[11,23],"called":[12],"AI":[13,73,93,108],"Queries,":[14],"enabling":[15],"users":[16],"specify":[18],"functions":[19],"conditions":[21],"in":[22,155,205],"that":[24,63,97,150,178,207,223],"are":[25],"evaluated":[26],"by":[27,213],"LLMs,":[28],"thereby":[29],"broadening":[30],"significantly":[31],"the":[32,40,119,152,173,211,215,225],"kinds":[33],"of":[34,42,82,90],"queries":[35,62,74],"one":[36],"can":[37,75],"express":[38],"over":[39,145],"combination":[41],"structured":[43,65],"unstructured":[45,67],"data.":[46,68],"LLMs":[47],"offer":[48],"remarkable":[49],"semantic":[50,120,129],"reasoning":[51],"capabilities,":[52],"making":[53],"them":[54],"an":[55,87,184],"essential":[56],"tool":[57],"for":[58,118,128,190,193],"complex":[59],"nuanced":[61],"blend":[64],"While":[69],"extremely":[70],"powerful,":[71],"these":[72,159],"become":[76],"prohibitively":[77],"costly":[78],"when":[79],"invoked":[80],"thousands":[81],"times.":[83],"This":[84],"paper":[85],"provides":[86],"extensive":[88],"evaluation":[89],"a":[91,200],"recent":[92],"query":[94],"approximation":[95],"approach":[96,111,192],"enables":[98],"low":[99],"cost":[100,114,133],"analytics":[101],"applications":[104],"benefit":[106],"from":[107,138],"queries.":[109],"The":[110,132],"delivers":[112],">100x":[113],"latency":[116,156,212],"reduction":[117],"filter":[121],"(AI.IF)":[122],"operator":[123],"also":[125],"important":[126],"gains":[127,136,154],"ranking":[130],"(AI.RANK).":[131],"performance":[135],"come":[137],"utilizing":[139],"cheap":[140],"accurate":[142],"proxy":[143,160,216,226],"models":[144,161],"embedding":[146],"vectors.":[147],"We":[148,182,220],"show":[149],"despite":[151],"massive":[153],"cost,":[158],"preserve":[162],"accuracy":[163,167],"occasionally":[165],"improve":[166,210],"across":[168],"various":[169],"benchmark":[170,177],"datasets,":[171],"including":[172],"extended":[174],"Amazon":[175],"reviews":[176],"has":[179],"10M":[180],"rows.":[181],"present":[183,221],"OLAP-friendly":[185],"architecture":[186,204],"within":[187],"Google":[188],"BigQuery":[189],"this":[191],"purely":[194],"online":[195],"(ad":[196],"hoc)":[197],"queries,":[198],"low-latency":[201],"HTAP":[202],"database-friendly":[203],"AlloyDB":[206],"could":[208],"further":[209],"moving":[214],"model":[217,227],"training":[218],"offline.":[219],"techniques":[222],"accelerate":[224],"training.":[228]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-03-20T00:00:00"}