{"id":"https://openalex.org/W3167477380","doi":"https://doi.org/10.1145/3448016.3457277","title":"Combining Aggregation and Sampling (Nearly) Optimally for Approximate Query Processing","display_name":"Combining Aggregation and Sampling (Nearly) Optimally for Approximate Query Processing","publication_year":2021,"publication_date":"2021-06-09","ids":{"openalex":"https://openalex.org/W3167477380","doi":"https://doi.org/10.1145/3448016.3457277","mag":"3167477380"},"language":"en","primary_location":{"id":"doi:10.1145/3448016.3457277","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3448016.3457277","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2021 International Conference on Management of Data","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/A5042597521","display_name":"Xi Liang","orcid":"https://orcid.org/0000-0002-7580-5933"},"institutions":[{"id":"https://openalex.org/I39422238","display_name":"University of Illinois Chicago","ror":"https://ror.org/02mpq6x41","country_code":"US","type":"education","lineage":["https://openalex.org/I39422238"]},{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Xi Liang","raw_affiliation_strings":["University of Chicago, Chicago, IL, USA"],"affiliations":[{"raw_affiliation_string":"University of Chicago, Chicago, IL, USA","institution_ids":["https://openalex.org/I40347166","https://openalex.org/I39422238"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015883931","display_name":"Stavros Sintos","orcid":"https://orcid.org/0000-0002-2114-8886"},"institutions":[{"id":"https://openalex.org/I39422238","display_name":"University of Illinois Chicago","ror":"https://ror.org/02mpq6x41","country_code":"US","type":"education","lineage":["https://openalex.org/I39422238"]},{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stavros Sintos","raw_affiliation_strings":["University of Chicago, Chicago, IL, USA"],"affiliations":[{"raw_affiliation_string":"University of Chicago, Chicago, IL, USA","institution_ids":["https://openalex.org/I40347166","https://openalex.org/I39422238"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038875368","display_name":"Zechao Shang","orcid":"https://orcid.org/0000-0002-6409-0792"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zechao Shang","raw_affiliation_strings":["Snowflake Computing, San Francisco, CA, USA"],"affiliations":[{"raw_affiliation_string":"Snowflake Computing, San Francisco, CA, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018480426","display_name":"Sanjay Krishnan","orcid":"https://orcid.org/0000-0001-6968-4090"},"institutions":[{"id":"https://openalex.org/I39422238","display_name":"University of Illinois Chicago","ror":"https://ror.org/02mpq6x41","country_code":"US","type":"education","lineage":["https://openalex.org/I39422238"]},{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sanjay Krishnan","raw_affiliation_strings":["University of Chicago, Chicago, IL, USA"],"affiliations":[{"raw_affiliation_string":"University of Chicago, Chicago, IL, USA","institution_ids":["https://openalex.org/I40347166","https://openalex.org/I39422238"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5042597521"],"corresponding_institution_ids":["https://openalex.org/I39422238","https://openalex.org/I40347166"],"apc_list":null,"apc_paid":null,"fwci":3.0564,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":{"value":0.91556699,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1129","last_page":"1141"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9997000098228455,"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":0.9997000098228455,"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/T11106","display_name":"Data Management and Algorithms","score":0.9997000098228455,"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"}},{"id":"https://openalex.org/T12761","display_name":"Data Stream Mining Techniques","score":0.9886999726295471,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/precomputation","display_name":"Precomputation","score":0.9144672155380249},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7477352023124695},{"id":"https://openalex.org/keywords/aggregate","display_name":"Aggregate (composite)","score":0.6509270071983337},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.624749481678009},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.530342698097229},{"id":"https://openalex.org/keywords/cover","display_name":"Cover (algebra)","score":0.4931561350822449},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.46820858120918274},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.4620901942253113},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.45101645588874817},{"id":"https://openalex.org/keywords/stratified-sampling","display_name":"Stratified sampling","score":0.4343033730983734},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.4063529968261719},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.221469908952713},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.1817092001438141},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.08332285284996033},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.07949098944664001}],"concepts":[{"id":"https://openalex.org/C159379195","wikidata":"https://www.wikidata.org/wiki/Q7239568","display_name":"Precomputation","level":3,"score":0.9144672155380249},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7477352023124695},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.6509270071983337},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.624749481678009},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.530342698097229},{"id":"https://openalex.org/C2780428219","wikidata":"https://www.wikidata.org/wiki/Q16952335","display_name":"Cover (algebra)","level":2,"score":0.4931561350822449},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.46820858120918274},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.4620901942253113},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.45101645588874817},{"id":"https://openalex.org/C49898467","wikidata":"https://www.wikidata.org/wiki/Q1517706","display_name":"Stratified sampling","level":2,"score":0.4343033730983734},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4063529968261719},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.221469908952713},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.1817092001438141},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.08332285284996033},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.07949098944664001},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","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/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","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/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3448016.3457277","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3448016.3457277","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2021 International Conference on Management of Data","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":39,"referenced_works":["https://openalex.org/W1577912117","https://openalex.org/W1592355944","https://openalex.org/W1975184797","https://openalex.org/W1981988185","https://openalex.org/W2008931591","https://openalex.org/W2037701287","https://openalex.org/W2071989194","https://openalex.org/W2072540320","https://openalex.org/W2091341267","https://openalex.org/W2117348908","https://openalex.org/W2152029707","https://openalex.org/W2161768947","https://openalex.org/W2199389590","https://openalex.org/W2295655272","https://openalex.org/W2296195275","https://openalex.org/W2296677182","https://openalex.org/W2429510775","https://openalex.org/W2436406362","https://openalex.org/W2512646345","https://openalex.org/W2604536700","https://openalex.org/W2613577383","https://openalex.org/W2732582420","https://openalex.org/W2795530455","https://openalex.org/W2798277312","https://openalex.org/W2798499404","https://openalex.org/W2970050155","https://openalex.org/W3011923615","https://openalex.org/W3032627613","https://openalex.org/W3081937877","https://openalex.org/W3100965700","https://openalex.org/W3123874245","https://openalex.org/W4205483682","https://openalex.org/W4237116537","https://openalex.org/W4288086218","https://openalex.org/W4291720394","https://openalex.org/W4291720518","https://openalex.org/W4299841484","https://openalex.org/W6635371082","https://openalex.org/W6638337754"],"related_works":["https://openalex.org/W2079151874","https://openalex.org/W3123827920","https://openalex.org/W2037382310","https://openalex.org/W4250438475","https://openalex.org/W2347278070","https://openalex.org/W2325459073","https://openalex.org/W2144058483","https://openalex.org/W2413529408","https://openalex.org/W1971531476","https://openalex.org/W3126132007"],"abstract_inverted_index":{"Sample-based":[0],"approximate":[1],"query":[2],"processing":[3],"(AQP)":[4],"suffers":[5],"from":[6],"many":[7],"pitfalls":[8],"such":[9,132],"as":[10],"the":[11,79,88,99,119,129],"inability":[12],"to":[13],"answer":[14],"very":[15],"selective":[16],"queries":[17,94],"and":[18,42,55,112],"unreliable":[19],"confidence":[20],"intervals":[21],"when":[22],"sample":[23],"sizes":[24],"are":[25,105,116],"small.":[26],"Recent":[27],"research":[28],"presented":[29],"an":[30,57,124],"intriguing":[31],"solution":[32,49],"of":[33,71,78,84,103],"combining":[34],"materialized,":[35],"pre-computed":[36],"aggregates":[37,73],"with":[38,98,108,118,136],"sampling":[39],"for":[40,90,126],"accurate":[41],"more":[43],"reliable":[44],"AQP.":[45],"We":[46,122],"explore":[47],"this":[48,53,85],"in":[50,52],"detail":[51],"work":[54],"propose":[56,123],"AQP":[58],"physical":[59],"design":[60],"called":[61],"PASS,":[62],"or":[63],"Precomputation-Assisted":[64],"Stratified":[65],"Sampling.":[66],"PASS":[67],"builds":[68],"a":[69,109,133],"tree":[70,86],"partial":[72,114],"that":[74],"cover":[75],"different":[76],"partitions":[77,100],"dataset.":[80],"The":[81],"leaf":[82],"nodes":[83],"form":[87],"strata":[89],"stratified":[91,120],"samples.":[92,121],"Aggregate":[93],"whose":[95],"predicates":[96],"align":[97],"(or":[101],"unions":[102],"partitions)":[104],"exactly":[106],"answered":[107],"depth-first":[110],"search,":[111],"any":[113],"overlaps":[115],"approximated":[117],"algorithm":[125],"optimally":[127],"partitioning":[128],"data":[130,134],"into":[131],"structure":[135],"various":[137],"practical":[138],"approximation":[139],"techniques.":[140]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}