{"id":"https://openalex.org/W3029541804","doi":"https://doi.org/10.1145/3318464.3389752","title":"The Case for a Learned Sorting Algorithm","display_name":"The Case for a Learned Sorting Algorithm","publication_year":2020,"publication_date":"2020-05-29","ids":{"openalex":"https://openalex.org/W3029541804","doi":"https://doi.org/10.1145/3318464.3389752","mag":"3029541804"},"language":"en","primary_location":{"id":"doi:10.1145/3318464.3389752","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3318464.3389752","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 ACM SIGMOD International Conference on Management of Data","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hdl.handle.net/1721.1/145664","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5007935841","display_name":"Ani Kristo","orcid":"https://orcid.org/0000-0003-4590-5607"},"institutions":[{"id":"https://openalex.org/I27804330","display_name":"Brown University","ror":"https://ror.org/05gq02987","country_code":"US","type":"education","lineage":["https://openalex.org/I27804330"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ani Kristo","raw_affiliation_strings":["Brown University, Providence, RI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brown University, Providence, RI, USA","institution_ids":["https://openalex.org/I27804330"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021956406","display_name":"Kapil Vaidya","orcid":"https://orcid.org/0009-0000-1435-5927"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kapil Vaidya","raw_affiliation_strings":["Massachusetts Institute of Technology, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109862110","display_name":"U\u011fur \u00c7etintemel","orcid":null},"institutions":[{"id":"https://openalex.org/I27804330","display_name":"Brown University","ror":"https://ror.org/05gq02987","country_code":"US","type":"education","lineage":["https://openalex.org/I27804330"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ugur \u00c7etintemel","raw_affiliation_strings":["Brown University, Providence, RI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brown University, Providence, RI, USA","institution_ids":["https://openalex.org/I27804330"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085992504","display_name":"Sanchit Misra","orcid":"https://orcid.org/0000-0001-7863-858X"},"institutions":[{"id":"https://openalex.org/I4210146682","display_name":"Intel (India)","ror":"https://ror.org/04f2n1245","country_code":"IN","type":"company","lineage":["https://openalex.org/I1343180700","https://openalex.org/I4210146682"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sanchit Misra","raw_affiliation_strings":["Intel Labs, Bangalore, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intel Labs, Bangalore, India","institution_ids":["https://openalex.org/I4210146682"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034086130","display_name":"Tim Kraska","orcid":"https://orcid.org/0009-0003-2414-2759"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tim Kraska","raw_affiliation_strings":["Massachusetts Institute of Technology, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.9269,"has_fulltext":false,"cited_by_count":44,"citation_normalized_percentile":{"value":0.94688831,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1001","last_page":"1016"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9998999834060669,"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":0.9998999834060669,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9994999766349792,"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/T10772","display_name":"Distributed systems and fault tolerance","score":0.9962000250816345,"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/merge-sort","display_name":"Merge sort","score":0.8444085121154785},{"id":"https://openalex.org/keywords/merge-algorithm","display_name":"Merge algorithm","score":0.8350494503974915},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8148416876792908},{"id":"https://openalex.org/keywords/sorting-algorithm","display_name":"Sorting algorithm","score":0.8126981258392334},{"id":"https://openalex.org/keywords/quicksort","display_name":"Quicksort","score":0.7760928869247437},{"id":"https://openalex.org/keywords/joins","display_name":"Joins","score":0.6054489612579346},{"id":"https://openalex.org/keywords/sort","display_name":"sort","score":0.5827308297157288},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5782991051673889},{"id":"https://openalex.org/keywords/sorting","display_name":"Sorting","score":0.5264699459075928},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4810069501399994},{"id":"https://openalex.org/keywords/pointer","display_name":"Pointer (user interface)","score":0.45991507172584534},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.4131864905357361},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3688884973526001},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.15738987922668457},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10838958621025085},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.1074647307395935},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.10289314389228821}],"concepts":[{"id":"https://openalex.org/C35555965","wikidata":"https://www.wikidata.org/wiki/Q189057","display_name":"Merge sort","level":4,"score":0.8444085121154785},{"id":"https://openalex.org/C140086265","wikidata":"https://www.wikidata.org/wiki/Q11341754","display_name":"Merge algorithm","level":4,"score":0.8350494503974915},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8148416876792908},{"id":"https://openalex.org/C108094655","wikidata":"https://www.wikidata.org/wiki/Q181593","display_name":"Sorting algorithm","level":3,"score":0.8126981258392334},{"id":"https://openalex.org/C2778937211","wikidata":"https://www.wikidata.org/wiki/Q486598","display_name":"Quicksort","level":4,"score":0.7760928869247437},{"id":"https://openalex.org/C2778692605","wikidata":"https://www.wikidata.org/wiki/Q4041866","display_name":"Joins","level":2,"score":0.6054489612579346},{"id":"https://openalex.org/C88548561","wikidata":"https://www.wikidata.org/wiki/Q347599","display_name":"sort","level":2,"score":0.5827308297157288},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5782991051673889},{"id":"https://openalex.org/C111696304","wikidata":"https://www.wikidata.org/wiki/Q2303697","display_name":"Sorting","level":2,"score":0.5264699459075928},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4810069501399994},{"id":"https://openalex.org/C150202949","wikidata":"https://www.wikidata.org/wiki/Q107602","display_name":"Pointer (user interface)","level":2,"score":0.45991507172584534},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.4131864905357361},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3688884973526001},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.15738987922668457},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10838958621025085},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.1074647307395935},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.10289314389228821}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3318464.3389752","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3318464.3389752","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 ACM SIGMOD International Conference on Management of Data","raw_type":"proceedings-article"},{"id":"pmh:oai:dspace.mit.edu:1721.1/145664","is_oa":true,"landing_page_url":"https://hdl.handle.net/1721.1/145664","pdf_url":null,"source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ACM|Proceedings of the 2020 ACM SIGMOD International Conference on Management of Data","raw_type":"http://purl.org/eprint/type/ConferencePaper"}],"best_oa_location":{"id":"pmh:oai:dspace.mit.edu:1721.1/145664","is_oa":true,"landing_page_url":"https://hdl.handle.net/1721.1/145664","pdf_url":null,"source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ACM|Proceedings of the 2020 ACM SIGMOD International Conference on Management of Data","raw_type":"http://purl.org/eprint/type/ConferencePaper"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1539580421","https://openalex.org/W1902965424","https://openalex.org/W1966648469","https://openalex.org/W2004671457","https://openalex.org/W2014268383","https://openalex.org/W2025533349","https://openalex.org/W2041055696","https://openalex.org/W2048305092","https://openalex.org/W2063543800","https://openalex.org/W2077229436","https://openalex.org/W2080388000","https://openalex.org/W2082695854","https://openalex.org/W2089632823","https://openalex.org/W2110940180","https://openalex.org/W2118020555","https://openalex.org/W2146005787","https://openalex.org/W2168961888","https://openalex.org/W2278783412","https://openalex.org/W2406955896","https://openalex.org/W2556668011","https://openalex.org/W2610365067","https://openalex.org/W2790625403","https://openalex.org/W2890276152","https://openalex.org/W2894818483","https://openalex.org/W2909813108","https://openalex.org/W2911540814","https://openalex.org/W2913631065","https://openalex.org/W2948233700","https://openalex.org/W2948936239","https://openalex.org/W2951465128","https://openalex.org/W2962771342","https://openalex.org/W2964316344","https://openalex.org/W2968986602","https://openalex.org/W2970148517","https://openalex.org/W3099158806","https://openalex.org/W3102117087","https://openalex.org/W3103567827","https://openalex.org/W3104921985"],"related_works":["https://openalex.org/W4320925713","https://openalex.org/W2552439138","https://openalex.org/W2765396134","https://openalex.org/W1493296159","https://openalex.org/W2093482277","https://openalex.org/W3029541804","https://openalex.org/W2575539670","https://openalex.org/W2240806428","https://openalex.org/W2057245959","https://openalex.org/W3037448952"],"abstract_inverted_index":{"Sorting":[0],"is":[1,145,166],"one":[2],"of":[3,27,41,49,53,66,163],"the":[4,50,54,67,79,83,167],"most":[5],"fundamental":[6],"algorithms":[7],"in":[8,15,82],"Computer":[9],"Science":[10],"and":[11,75,116,156,173],"a":[12,38,46,59,89,104,160],"common":[13,113],"operation":[14],"databases":[16],"not":[17],"just":[18],"for":[19,71,120,171],"sorting":[20,91,114,169],"query":[21],"results":[22,129],"but":[23],"also":[24],"as":[25],"part":[26],"joins":[28],"(i.e.,":[29],"sort-merge-join)":[30],"or":[31],"indexing.":[32],"In":[33],"this":[34,110],"work,":[35],"we":[36],"introduce":[37],"new":[39],"type":[40],"distribution":[42],"sort":[43],"that":[44,93,131],"leverages":[45],"learned":[47],"model":[48,60],"empirical":[51,69],"CDF":[52,70],"data.":[55],"Our":[56],"algorithm":[57,92,111],"uses":[58],"to":[61,78,102,122],"efficiently":[62],"get":[63],"an":[64,135,146],"approximation":[65],"scaled":[68],"each":[72],"record":[73],"key":[74],"map":[76],"it":[77],"corresponding":[80],"position":[81],"output":[84],"array.":[85],"We":[86,108],"then":[87],"apply":[88],"deterministic":[90],"works":[94],"well":[95],"on":[96],"nearly-sorted":[97],"arrays":[98],"(e.g.,":[99],"Insertion":[100],"Sort)":[101],"establish":[103],"totally":[105],"sorted":[106],"order.":[107],"compared":[109],"against":[112],"approaches":[115],"measured":[117],"its":[118],"performance":[119,138],"up":[121],"1":[123],"billion":[124],"normally-distributed":[125],"double-precision":[126],"keys.":[127],"The":[128],"show":[130],"our":[132],"approach":[133],"yields":[134],"average":[136],"3.38x":[137],"improvement":[139,151,158],"over":[140,152,159],"C++":[141,161],"STL":[142],"sort,":[143],"which":[144,165],"optimized":[147],"Quicksort":[148],"hybrid,":[149],"1.49x":[150],"sequential":[153],"Radix":[154],"Sort,":[155],"5.54x":[157],"implementation":[162],"Timsort,":[164],"default":[168],"function":[170],"Java":[172],"Python.":[174]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}