{"id":"https://openalex.org/W4414041780","doi":"https://doi.org/10.14778/3746405.3746431","title":"<i>Stochastic SketchRefine</i> : Scaling In-Database Decision-Making under Uncertainty to Millions of Tuples","display_name":"<i>Stochastic SketchRefine</i> : Scaling In-Database Decision-Making under Uncertainty to Millions of Tuples","publication_year":2025,"publication_date":"2025-05-01","ids":{"openalex":"https://openalex.org/W4414041780","doi":"https://doi.org/10.14778/3746405.3746431"},"language":"en","primary_location":{"id":"doi:10.14778/3746405.3746431","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3746405.3746431","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/A5055514521","display_name":"Riddho Ridwanul Haque","orcid":null},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Riddho R. Haque","raw_affiliation_strings":["University of Massachusetts Amherst"],"affiliations":[{"raw_affiliation_string":"University of Massachusetts Amherst","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111578658","display_name":"A. L.","orcid":null},"institutions":[{"id":"https://openalex.org/I120250893","display_name":"New York University Abu Dhabi","ror":"https://ror.org/00e5k0821","country_code":"AE","type":"education","lineage":["https://openalex.org/I120250893","https://openalex.org/I57206974"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Anh L. Mai","raw_affiliation_strings":["NYU Abu Dhabi"],"affiliations":[{"raw_affiliation_string":"NYU Abu Dhabi","institution_ids":["https://openalex.org/I120250893"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072749095","display_name":"Matteo Brucato","orcid":"https://orcid.org/0000-0003-2730-6432"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Matteo Brucato","raw_affiliation_strings":["Microsoft Research"],"affiliations":[{"raw_affiliation_string":"Microsoft Research","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044418740","display_name":"Azza Abouzied","orcid":"https://orcid.org/0000-0003-4273-2536"},"institutions":[{"id":"https://openalex.org/I120250893","display_name":"New York University Abu Dhabi","ror":"https://ror.org/00e5k0821","country_code":"AE","type":"education","lineage":["https://openalex.org/I120250893","https://openalex.org/I57206974"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Azza Abouzied","raw_affiliation_strings":["NYU Abu Dhabi"],"affiliations":[{"raw_affiliation_string":"NYU Abu Dhabi","institution_ids":["https://openalex.org/I120250893"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090729930","display_name":"Peter J. Haas","orcid":"https://orcid.org/0000-0001-5694-3065"},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peter J. Haas","raw_affiliation_strings":["University of Massachusetts Amherst"],"affiliations":[{"raw_affiliation_string":"University of Massachusetts Amherst","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019048013","display_name":"Alexandra Meliou","orcid":"https://orcid.org/0000-0001-7346-6002"},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alexandra Meliou","raw_affiliation_strings":["University of Massachusetts Amherst"],"affiliations":[{"raw_affiliation_string":"University of Massachusetts Amherst","institution_ids":["https://openalex.org/I24603500"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5055514521"],"corresponding_institution_ids":["https://openalex.org/I24603500"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.31060725,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"18","issue":"9","first_page":"3106","last_page":"3118"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9998000264167786,"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":0.9998000264167786,"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/T11596","display_name":"Constraint Satisfaction and Optimization","score":0.9854000210762024,"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/T10698","display_name":"Transportation Planning and Optimization","score":0.9819999933242798,"subfield":{"id":"https://openalex.org/subfields/3313","display_name":"Transportation"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/tuple","display_name":"Tuple","score":0.5895000100135803},{"id":"https://openalex.org/keywords/stochastic-optimization","display_name":"Stochastic optimization","score":0.5809000134468079},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5462999939918518},{"id":"https://openalex.org/keywords/stochastic-programming","display_name":"Stochastic programming","score":0.4839000105857849},{"id":"https://openalex.org/keywords/optimization-problem","display_name":"Optimization problem","score":0.44699999690055847},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.42260000109672546},{"id":"https://openalex.org/keywords/stochastic-process","display_name":"Stochastic process","score":0.40369999408721924},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.3847000002861023},{"id":"https://openalex.org/keywords/integer","display_name":"Integer (computer science)","score":0.38190001249313354}],"concepts":[{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.6543999910354614},{"id":"https://openalex.org/C118930307","wikidata":"https://www.wikidata.org/wiki/Q600590","display_name":"Tuple","level":2,"score":0.5895000100135803},{"id":"https://openalex.org/C194387892","wikidata":"https://www.wikidata.org/wiki/Q1747770","display_name":"Stochastic optimization","level":2,"score":0.5809000134468079},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5529000163078308},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5462999939918518},{"id":"https://openalex.org/C137631369","wikidata":"https://www.wikidata.org/wiki/Q7617831","display_name":"Stochastic programming","level":2,"score":0.4839000105857849},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.44699999690055847},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.42260000109672546},{"id":"https://openalex.org/C8272713","wikidata":"https://www.wikidata.org/wiki/Q176737","display_name":"Stochastic process","level":2,"score":0.40369999408721924},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.3847000002861023},{"id":"https://openalex.org/C97137487","wikidata":"https://www.wikidata.org/wiki/Q729138","display_name":"Integer (computer science)","level":2,"score":0.38190001249313354},{"id":"https://openalex.org/C41045048","wikidata":"https://www.wikidata.org/wiki/Q202843","display_name":"Linear programming","level":2,"score":0.37229999899864197},{"id":"https://openalex.org/C62644790","wikidata":"https://www.wikidata.org/wiki/Q3454689","display_name":"Variance reduction","level":3,"score":0.34850001335144043},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.34369999170303345},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.33880001306533813},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.32100000977516174},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.3203999996185303},{"id":"https://openalex.org/C71559656","wikidata":"https://www.wikidata.org/wiki/Q671298","display_name":"Divide and conquer algorithms","level":2,"score":0.3019999861717224},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.30140000581741333},{"id":"https://openalex.org/C129848803","wikidata":"https://www.wikidata.org/wiki/Q2564360","display_name":"Sample size determination","level":2,"score":0.29670000076293945},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.29350000619888306},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.2842999994754791},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.27959999442100525},{"id":"https://openalex.org/C56086750","wikidata":"https://www.wikidata.org/wiki/Q6042592","display_name":"Integer programming","level":2,"score":0.27399998903274536},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.27390000224113464},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2614000141620636},{"id":"https://openalex.org/C193254401","wikidata":"https://www.wikidata.org/wiki/Q2160088","display_name":"Robust optimization","level":2,"score":0.2612999975681305},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.259799987077713},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.2583000063896179},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.2578999996185303},{"id":"https://openalex.org/C55479107","wikidata":"https://www.wikidata.org/wiki/Q97663916","display_name":"Stochastic approximation","level":3,"score":0.251800000667572}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14778/3746405.3746431","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3746405.3746431","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W600148761","https://openalex.org/W1496151277","https://openalex.org/W1574922246","https://openalex.org/W1969248194","https://openalex.org/W1983221302","https://openalex.org/W2030276074","https://openalex.org/W2057237348","https://openalex.org/W2066778083","https://openalex.org/W2071009745","https://openalex.org/W2078686663","https://openalex.org/W2080816440","https://openalex.org/W2086128349","https://openalex.org/W2171660758","https://openalex.org/W2406551241","https://openalex.org/W2488157181","https://openalex.org/W2554106722","https://openalex.org/W2765539780","https://openalex.org/W2911585132","https://openalex.org/W3029651391","https://openalex.org/W3159249382","https://openalex.org/W3202302059","https://openalex.org/W4230471307","https://openalex.org/W4250913065","https://openalex.org/W4282040141","https://openalex.org/W4292928781","https://openalex.org/W4396571370","https://openalex.org/W4411442505"],"related_works":["https://openalex.org/W4254717236","https://openalex.org/W2377757044","https://openalex.org/W3160952126","https://openalex.org/W2320103255","https://openalex.org/W798918733","https://openalex.org/W4213167601","https://openalex.org/W2101287851","https://openalex.org/W105267264","https://openalex.org/W163279402","https://openalex.org/W2403168774"],"abstract_inverted_index":{"Decision":[0],"making":[1],"under":[2],"uncertainty":[3],"often":[4],"requires":[5],"choosing":[6],"packages":[7,55,212],",":[8,41],"or":[9,42],"bags":[10],"of":[11,45,49,65,74,91,100,131,161,164,199,215,222],"tuples,":[12,52],"that":[13,186],"collectively":[14],"optimize":[15],"expected":[16],"outcomes":[17],"while":[18],"limiting":[19],"risks.":[20],"Processing":[21],"Stochastic":[22,179,208],"Package":[23],"Queries":[24],"(SPQs)":[25],"involves":[26],"solving":[27],"very":[28],"large":[29,113,190],"optimization":[30,76,93,192],"problems":[31],"on":[32,112],"uncertain":[33],"data.":[34],"Monte":[35],"Carlo":[36],"methods":[37],"create":[38],"numerous":[39],"scenarios":[40,66,165],"sample":[43],"realizations":[44],"the":[46,51,72,75,85,88,92,98,103,123,162,220,223],"stochastic":[47,116,191],"attributes":[48,117],"all":[50],"and":[53,87,173,183,207],"generate":[54],"with":[56,82,97,118],"optimal":[57],"objective":[58],"values":[59],"across":[60],"these":[61,168],"scenarios.":[62],"The":[63],"number":[64,99,163],"needed":[67],"for":[68],"accurate":[69],"approximation\u2014and":[70],"hence":[71],"size":[73,158],"problem":[77,94,193],"when":[78],"using":[79],"prior":[80],"methods\u2014increases":[81],"variance":[83],"in":[84,102,213],"data,":[86],"search":[89],"space":[90],"increases":[95],"exponentially":[96],"tuples":[101],"relation.":[104],"Existing":[105],"solvers":[106],"take":[107],"hours":[108],"to":[109,126],"process":[110],"SPQs":[111,151],"relations":[114],"containing":[115],"high":[119],"variance.":[120],"Besides":[121],"enriching":[122],"SPaQL":[124],"language":[125],"capture":[127],"a":[128,181,189],"broader":[129],"class":[130],"risk":[132],"specifications,":[133],"we":[134,144,177],"make":[135],"two":[136],"fundamental":[137],"contributions":[138],"toward":[139],"scalable":[140],"SPQ":[141],"processing.":[142],"First,":[143],"propose":[145,178],"risk-constraint":[146],"linearization":[147],"(RCL),":[148],"which":[149],"converts":[150],"into":[152,194],"Integer":[153],"Linear":[154],"Programs":[155],"(ILPs)":[156],"whose":[157],"is":[159],"independent":[160],"used.":[166],"Solving":[167],"ILPs":[169],"gives":[170],"us":[171],"feasible":[172],"near-optimal":[174],"packages.":[175],"Second,":[176],"SketchRefine,":[180],"divide":[182],"conquer":[184],"framework":[185],"breaks":[187],"down":[188],"subproblems":[195],"involving":[196],"smaller":[197],"subsets":[198],"tuples.":[200],"Our":[201],"experiments":[202],"show":[203],"that,":[204],"together,":[205],"RCL":[206],"SketchRefine":[209],"produce":[210],"high-quality":[211],"orders":[214],"magnitude":[216],"lower":[217],"runtime":[218],"than":[219],"state":[221],"art.":[224]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-10T00:00:00"}