{"id":"https://openalex.org/W4221142004","doi":"https://doi.org/10.1145/3514221.3517885","title":"Balsa: Learning a Query Optimizer Without Expert Demonstrations","display_name":"Balsa: Learning a Query Optimizer Without Expert Demonstrations","publication_year":2022,"publication_date":"2022-06-10","ids":{"openalex":"https://openalex.org/W4221142004","doi":"https://doi.org/10.1145/3514221.3517885"},"language":"en","primary_location":{"id":"doi:10.1145/3514221.3517885","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3514221.3517885","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3514221.3517885","source":{"id":"https://openalex.org/S4363608845","display_name":"Proceedings of the 2022 International Conference on Management of Data","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 International Conference on Management of Data","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3514221.3517885","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103011963","display_name":"Zongheng Yang","orcid":"https://orcid.org/0000-0001-8716-8743"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zongheng Yang","raw_affiliation_strings":["University of California, Berkeley, Berkeley, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of California, Berkeley, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009640963","display_name":"Wei-Lin Chiang","orcid":"https://orcid.org/0009-0009-0105-723X"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wei-Lin Chiang","raw_affiliation_strings":["University of California, Berkeley, Berkeley, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of California, Berkeley, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057622403","display_name":"Sifei Luan","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sifei Luan","raw_affiliation_strings":["University of California, Berkeley, Berkeley, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of California, Berkeley, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024108438","display_name":"Gautam Mittal","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gautam Mittal","raw_affiliation_strings":["University of California, Berkeley, Berkeley, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of California, Berkeley, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035392658","display_name":"Michael Luo","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Luo","raw_affiliation_strings":["University of California, Berkeley, Berkeley, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of California, Berkeley, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041920173","display_name":"Ion Stoica","orcid":"https://orcid.org/0000-0002-5373-0088"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ion Stoica","raw_affiliation_strings":["University of California, Berkeley, Berkeley, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of California, Berkeley, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5103011963"],"corresponding_institution_ids":["https://openalex.org/I95457486"],"apc_list":null,"apc_paid":null,"fwci":7.9039,"has_fulltext":true,"cited_by_count":70,"citation_normalized_percentile":{"value":0.98520151,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"931","last_page":"944"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9975000023841858,"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"}},"topics":[{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9975000023841858,"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/T12288","display_name":"Optimization and Search Problems","score":0.9966999888420105,"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":0.9965999722480774,"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/computer-science","display_name":"Computer science","score":0.8674972057342529},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7259833812713623},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.6398435235023499},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5996941924095154},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.49778056144714355},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4928903579711914},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4559084475040436},{"id":"https://openalex.org/keywords/query-optimization","display_name":"Query optimization","score":0.4322241544723511},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.25427383184432983},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.14701929688453674}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8674972057342529},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7259833812713623},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.6398435235023499},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5996941924095154},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.49778056144714355},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4928903579711914},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4559084475040436},{"id":"https://openalex.org/C157692150","wikidata":"https://www.wikidata.org/wiki/Q2919848","display_name":"Query optimization","level":2,"score":0.4322241544723511},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.25427383184432983},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.14701929688453674},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3514221.3517885","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3514221.3517885","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3514221.3517885","source":{"id":"https://openalex.org/S4363608845","display_name":"Proceedings of the 2022 International Conference on Management of Data","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 International Conference on Management of Data","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2201.01441","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2201.01441","pdf_url":"https://arxiv.org/pdf/2201.01441","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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:10.1145/3514221.3517885","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3514221.3517885","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3514221.3517885","source":{"id":"https://openalex.org/S4363608845","display_name":"Proceedings of the 2022 International Conference on Management of Data","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 International Conference on Management of Data","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4221142004.pdf","grobid_xml":"https://content.openalex.org/works/W4221142004.grobid-xml"},"referenced_works_count":39,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W251375015","https://openalex.org/W1556146035","https://openalex.org/W2106856755","https://openalex.org/W2257979135","https://openalex.org/W2396309311","https://openalex.org/W2605102758","https://openalex.org/W2618097077","https://openalex.org/W2755385361","https://openalex.org/W2766447205","https://openalex.org/W2889503624","https://openalex.org/W2890276152","https://openalex.org/W2911540814","https://openalex.org/W2955798121","https://openalex.org/W2961619211","https://openalex.org/W2970148517","https://openalex.org/W2971806123","https://openalex.org/W2981030070","https://openalex.org/W2982316857","https://openalex.org/W2991530444","https://openalex.org/W2998249308","https://openalex.org/W3029327553","https://openalex.org/W3035622927","https://openalex.org/W3082494217","https://openalex.org/W3097225903","https://openalex.org/W3099273181","https://openalex.org/W3100925961","https://openalex.org/W3118210634","https://openalex.org/W3124277639","https://openalex.org/W3129744650","https://openalex.org/W3176153696","https://openalex.org/W3203329898","https://openalex.org/W3210084676","https://openalex.org/W4232672600","https://openalex.org/W4287671158","https://openalex.org/W4289703391","https://openalex.org/W4295830359","https://openalex.org/W4301464423","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W2000785801","https://openalex.org/W986318368","https://openalex.org/W2378211422","https://openalex.org/W2384410913","https://openalex.org/W2352878646","https://openalex.org/W2004734601","https://openalex.org/W2130149817","https://openalex.org/W2990194547","https://openalex.org/W1480123525","https://openalex.org/W2620865396"],"abstract_inverted_index":{"Query":[0],"optimizers":[1,14,131],"are":[2],"a":[3,52,66,111],"performance-critical":[4],"component":[5],"in":[6,74,107,125],"every":[7],"database":[8],"system.":[9],"Due":[10],"to":[11,18,22,35,105,123],"their":[12],"complexity,":[13],"take":[15],"experts":[16],"months":[17],"write":[19],"and":[20,47,93,100],"years":[21],"refine.":[23],"In":[24],"this":[25],"work,":[26],"we":[27],"demonstrate":[28],"for":[29],"the":[30,78,84,118],"first":[31,61],"time":[32],"that":[33],"learning":[34,39,73,122],"optimize":[36,124],"queries":[37],"without":[38],"from":[40,65],"an":[41],"expert":[42,88],"optimizer":[43,54],"is":[44],"both":[45,91],"possible":[46],"efficient.":[48],"We":[49],"present":[50],"Balsa,":[51],"query":[53,89],"built":[55],"by":[56,71,103],"deep":[57],"reinforcement":[58],"learning.":[59],"Balsa":[60,82,115],"learns":[62],"basic":[63],"knowledge":[64],"simple,":[67],"environment-agnostic":[68],"simulator,":[69],"followed":[70],"safe":[72],"real":[75],"execution.":[76],"On":[77],"Join":[79],"Order":[80],"Benchmark,":[81],"matches":[83],"performance":[85],"of":[86,98,120],"two":[87,96],"optimizers,":[90],"open-source":[92],"commercial,":[94],"with":[95],"hours":[97],"learning,":[99],"outperforms":[101],"them":[102],"up":[104],"2.8\u00d7":[106],"workload":[108],"runtime":[109],"after":[110],"few":[112],"more":[113],"hours.":[114],"thus":[116],"opens":[117],"possibility":[119],"automatically":[121],"future":[126],"compute":[127],"environments":[128],"where":[129],"expert-designed":[130],"do":[132],"not":[133],"exist.":[134]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":28},{"year":2024,"cited_by_count":29},{"year":2023,"cited_by_count":8}],"updated_date":"2026-04-04T08:04:53.788161","created_date":"2025-10-10T00:00:00"}