{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T10:52:32Z","timestamp":1790765552184,"version":"4.1.0"},"publisher-location":"New York, NY, USA","reference-count":47,"publisher":"ACM","license":[{"start":{"date-parts":[[2020,5,31]],"date-time":"2020-05-31T00:00:00Z","timestamp":1590883200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2020,6,11]]},"DOI":"10.1145\/3318464.3380584","type":"proceedings-article","created":{"date-parts":[[2020,5,29]],"date-time":"2020-05-29T13:12:33Z","timestamp":1590757953000},"page":"99-113","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":74,"title":["Cost Models for Big Data Query Processing: Learning, Retrofitting, and Our Findings"],"prefix":"10.1145","author":[{"given":"Tarique","family":"Siddiqui","sequence":"first","affiliation":[{"name":"Microsoft & University of Illinois at Urbana-Champaign, Urbana, IL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alekh","family":"Jindal","sequence":"additional","affiliation":[{"name":"Microsoft, Redmond, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shi","family":"Qiao","sequence":"additional","affiliation":[{"name":"Microsoft, Redmond, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hiren","family":"Patel","sequence":"additional","affiliation":[{"name":"Microsoft, Redmond, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wangchao","family":"Le","sequence":"additional","affiliation":[{"name":"Microsoft, Redmond, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2020,5,31]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.5555\/2228298.2228327"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2012.64"},{"key":"e_1_3_2_2_3_1","first-page":"4","volume-title":"NSDI","volume":"2","author":"Alipourfard O.","year":"2017","unstructured":"O. Alipourfard , H. H. Liu , J. Chen , S. Venkataraman , M. Yu , and M. Zhang . Cherrypick: Adaptively unearthing the best cloud configurations for big data analytics . In NSDI , volume 2 , pages 4 -- 2 , 2017 . O. Alipourfard, H. H. Liu, J. Chen, S. Venkataraman, M. Yu, and M. Zhang. Cherrypick: Adaptively unearthing the best cloud configurations for big data analytics. In NSDI, volume 2, pages 4--2, 2017."},{"key":"e_1_3_2_2_4_1","unstructured":"AWS Athena. https:\/\/aws.amazon.com\/athena\/.  AWS Athena. https:\/\/aws.amazon.com\/athena\/."},{"key":"e_1_3_2_2_5_1","volume-title":"Kernel independent component analysis. Journal of machine learning research, 3(Jul):1--48","author":"Bach F. R.","year":"2002","unstructured":"F. R. Bach and M. I. Jordan . Kernel independent component analysis. Journal of machine learning research, 3(Jul):1--48 , 2002 . F. R. Bach and M. I. Jordan. Kernel independent component analysis. Journal of machine learning research, 3(Jul):1--48, 2002."},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/2213836.2213959"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.14778\/2536222.2536223"},{"issue":"1","key":"e_1_3_2_2_8_1","first-page":"46","volume":"36","author":"Bruno N.","year":"2013","unstructured":"N. Bruno , S. Jain , and J. Zhou . Recurring Job Optimization for Massively Distributed Query Processing. IEEE Data Eng. Bull. , 36 ( 1 ): 46 -- 55 , 2013 . N. Bruno, S. Jain, and J. Zhou. Recurring Job Optimization for Massively Distributed Query Processing. IEEE Data Eng. Bull., 36(1):46--55, 2013.","journal-title":"Recurring Job Optimization for Massively Distributed Query Processing. IEEE Data Eng. Bull."},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.14778\/2733004.2733020"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.14778\/1454159.1454166"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/1007568.1007659"},{"key":"e_1_3_2_2_12_1","unstructured":"CLEO\n  : Technical Report. http:\/\/arxiv.org\/abs\/2002.12393.  CLEO: Technical Report. http:\/\/arxiv.org\/abs\/2002.12393."},{"issue":"9","key":"e_1_3_2_2_13_1","first-page":"1044","volume":"12","author":"Dutt A.","year":"2019","unstructured":"A. Dutt , C. Wang , A. Nazi , S. Kandula , V. Narasayya , and S. Chaudhuri . Selectivity Estimation for Range Predicates Using Lightweight Models. PVLDB , 12 ( 9 ): 1044 -- 1057 , 2019 . A. Dutt, C. Wang, A. Nazi, S. Kandula, V. Narasayya, and S. Chaudhuri. Selectivity Estimation for Range Predicates Using Lightweight Models. PVLDB, 12(9):1044--1057, 2019.","journal-title":"Selectivity Estimation for Range Predicates Using Lightweight Models. PVLDB"},{"key":"e_1_3_2_2_14_1","unstructured":"FastTree. https:\/\/www.nuget.org\/packages\/Microsoft.ML.FastTree\/.  FastTree. https:\/\/www.nuget.org\/packages\/Microsoft.ML.FastTree\/."},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/2168836.2168847"},{"key":"e_1_3_2_2_16_1","volume-title":"Stochastic gradient boosting. Computational statistics & data analysis, 38(4):367--378","author":"Friedman J. H.","year":"2002","unstructured":"J. H. Friedman . Stochastic gradient boosting. Computational statistics & data analysis, 38(4):367--378 , 2002 . J. H. Friedman. Stochastic gradient boosting. Computational statistics & data analysis, 38(4):367--378, 2002."},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2009.130"},{"key":"e_1_3_2_2_18_1","unstructured":"Google BigQuery. https:\/\/cloud.google.com\/bigquery.  Google BigQuery. https:\/\/cloud.google.com\/bigquery."},{"issue":"3","key":"e_1_3_2_2_19_1","first-page":"19","article-title":"The Cascades framework for query optimization","volume":"18","author":"Graefe G.","year":"1995","unstructured":"G. Graefe . The Cascades framework for query optimization . IEEE Data Eng. Bull. , 18 ( 3 ): 19 -- 29 , 1995 . G. Graefe. The Cascades framework for query optimization. IEEE Data Eng. Bull., 18(3):19--29, 1995.","journal-title":"IEEE Data Eng. Bull."},{"key":"e_1_3_2_2_20_1","unstructured":"IBM BigSQL. https:\/\/www.ibm.com\/products\/db2-big-sql.  IBM BigSQL. https:\/\/www.ibm.com\/products\/db2-big-sql."},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.14778\/3192965.3192971"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3183713.3190656"},{"key":"e_1_3_2_2_23_1","first-page":"117","volume-title":"12th USENIX Symposium on Operating Systems Design and Implementation (OSDI 16)","author":"Jyothi S. A.","year":"2016","unstructured":"S. A. Jyothi , C. Curino , I. Menache , S. M. Narayanamurthy , A. Tumanov , J. Yaniv , R. Mavlyutov , \u00cd. Goiri, S. Krishnan , J. Kulkarni , : Towards automated slos for enterprise clusters . In 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI 16) , pages 117 -- 134 , 2016 . S. A. Jyothi, C. Curino, I. Menache, S. M. Narayanamurthy, A. Tumanov, J. Yaniv, R. Mavlyutov, \u00cd. Goiri, S. Krishnan, J. Kulkarni, et al. Morpheus: Towards automated slos for enterprise clusters. In 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI 16), pages 117--134, 2016."},{"key":"e_1_3_2_2_24_1","volume-title":"CIDR","author":"Kipf A.","year":"2019","unstructured":"A. Kipf , T. Kipf , B. Radke , V. Leis , P. Boncz , and A. Kemper . Learned cardinalities: Estimating correlated joins with deep learning . CIDR , 2019 . A. Kipf, T. Kipf, B. Radke, V. Leis, P. Boncz, and A. Kemper. Learned cardinalities: Estimating correlated joins with deep learning. CIDR, 2019."},{"key":"e_1_3_2_2_25_1","volume-title":"CIDR","author":"Kraska T.","year":"2019","unstructured":"T. Kraska , M. Alizadeh , A. Beutel , E. Chi , J. Ding , A. Kristo , G. Leclerc , S. Madden , H. Mao , and V. Nathan . Sagedb: A learned database system . CIDR , 2019 . T. Kraska, M. Alizadeh, A. Beutel, E. Chi, J. Ding, A. Kristo, G. Leclerc, S. Madden, H. Mao, and V. Nathan. Sagedb: A learned database system. CIDR, 2019."},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3183713.3196909"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.14778\/2733004.2733037"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.14778\/2850583.2850594"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.14778\/2350229.2350269"},{"key":"e_1_3_2_2_30_1","volume-title":"Proc. Workshop on Database Query Optimization","volume":"13","author":"Lohman G.","year":"2014","unstructured":"G. Lohman . Is query optimization a \"solved\" problem . In Proc. Workshop on Database Query Optimization , volume 13 . Oregon Graduate Center Comp. Sci. Tech. Rep , 2014 . G. Lohman. Is query optimization a \"solved\" problem. In Proc. Workshop on Database Query Optimization, volume 13. Oregon Graduate Center Comp. Sci. Tech. Rep, 2014."},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/1007568.1007658"},{"key":"e_1_3_2_2_32_1","volume-title":"Neo: A learned query optimizer. arXiv preprint arXiv:1904.03711","author":"Marcus R.","year":"2019","unstructured":"R. Marcus , P. Negi , H. Mao , C. Zhang , M. Alizadeh , T. Kraska , O. Papaemmanouil , and N. Tatbul . Neo: A learned query optimizer. arXiv preprint arXiv:1904.03711 , 2019 . R. Marcus, P. Negi, H. Mao, C. Zhang, M. Alizadeh, T. Kraska, O. Papaemmanouil, and N. Tatbul. Neo: A learned query optimizer. arXiv preprint arXiv:1904.03711, 2019."},{"key":"e_1_3_2_2_33_1","unstructured":"MART. http:\/\/statweb.stanford.edu\/jhf\/MART.html.  MART. http:\/\/statweb.stanford.edu\/jhf\/MART.html."},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/369275.369291"},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/2987550.2987566"},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3035918.3056100"},{"issue":"12","key":"e_1_3_2_2_37_1","first-page":"1850","volume":"12","author":"Roy A.","year":"2019","unstructured":"A. Roy , A. Jindal , H. Patel , A. Gosalia , S. Krishnan , and C. Curino . SparkCruise: Handsfree Computation Reuse in Spark. PVLDB , 12 ( 12 ): 1850 -- 1853 , 2019 . A. Roy, A. Jindal, H. Patel, A. Gosalia, S. Krishnan, and C. Curino. SparkCruise: Handsfree Computation Reuse in Spark. PVLDB, 12(12):1850--1853, 2019.","journal-title":"SparkCruise: Handsfree Computation Reuse in Spark. PVLDB"},{"key":"e_1_3_2_2_38_1","volume-title":"Runtime Measurements in the Cloud: Observing, Analyzing, and Reducing Variance. PVLDB, 3(1--2):460--471","author":"Schad J.","year":"2010","unstructured":"J. Schad , J. Dittrich , and J.-A. Quian\u00e9-Ruiz . Runtime Measurements in the Cloud: Observing, Analyzing, and Reducing Variance. PVLDB, 3(1--2):460--471 , 2010 . J. Schad, J. Dittrich, and J.-A. Quian\u00e9-Ruiz. Runtime Measurements in the Cloud: Observing, Analyzing, and Reducing Variance. PVLDB, 3(1--2):460--471, 2010."},{"key":"e_1_3_2_2_39_1","first-page":"19","volume-title":"VLDB","volume":"1","author":"Stillger M.","year":"2001","unstructured":"M. Stillger , G. M. Lohman , V. Markl , and M. Kandil . Leo-db2's learning optimizer . In VLDB , volume 1 , pages 19 -- 28 , 2001 . M. Stillger, G. M. Lohman, V. Markl, and M. Kandil. Leo-db2's learning optimizer. In VLDB, volume 1, pages 19--28, 2001."},{"key":"e_1_3_2_2_40_1","first-page":"363","volume-title":"NSDI","author":"Venkataraman S.","year":"2016","unstructured":"S. Venkataraman and others. Ernest : Efficient performance prediction for large-scale advanced analytics . In NSDI , pages 363 -- 378 , 2016 . S. Venkataraman and others. Ernest: Efficient performance prediction for large-scale advanced analytics. In NSDI, pages 363--378, 2016."},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2018.00156"},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.14778\/3291264.3291267"},{"issue":"4","key":"e_1_3_2_2_43_1","first-page":"446","volume":"12","author":"Xin D.","year":"2018","unstructured":"D. Xin , S. Macke , L. Ma , J. Liu , S. Song , and A. Parameswaran . HELIX: Holistic Optimization for Accelerating Iterative Machine Learning. PVLDB , 12 ( 4 ): 446 -- 460 , 2018 . D. Xin, S. Macke, L. Ma, J. Liu, S. Song, and A. Parameswaran. HELIX: Holistic Optimization for Accelerating Iterative Machine Learning. PVLDB, 12(4):446--460, 2018.","journal-title":"HELIX: Holistic Optimization for Accelerating Iterative Machine Learning. PVLDB"},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.14778\/3192965.3192967"},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00778-012-0280-z"},{"key":"e_1_3_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.14778\/3342263.3342267"},{"key":"e_1_3_2_2_47_1","volume-title":"Regularization and variable selection via the elastic net. Journal of the royal statistical society: series B (statistical methodology), 67(2):301--320","author":"Zou H.","year":"2005","unstructured":"H. Zou and T. Hastie . Regularization and variable selection via the elastic net. Journal of the royal statistical society: series B (statistical methodology), 67(2):301--320 , 2005 . H. Zou and T. Hastie. Regularization and variable selection via the elastic net. Journal of the royal statistical society: series B (statistical methodology), 67(2):301--320, 2005."}],"event":{"name":"SIGMOD\/PODS '20: International Conference on Management of Data","location":"Portland OR USA","acronym":"SIGMOD\/PODS '20","sponsor":["SIGMOD ACM Special Interest Group on Management of Data"]},"container-title":["Proceedings of the 2020 ACM SIGMOD International Conference on Management of Data"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3318464.3380584","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3318464.3380584","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T21:01:52Z","timestamp":1750194112000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3318464.3380584"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5,31]]},"references-count":47,"alternative-id":["10.1145\/3318464.3380584","10.1145\/3318464"],"URL":"https:\/\/doi.org\/10.1145\/3318464.3380584","relation":{},"subject":[],"published":{"date-parts":[[2020,5,31]]},"assertion":[{"value":"2020-05-31","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}