{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,5]],"date-time":"2025-07-05T04:14:08Z","timestamp":1751688848993,"version":"3.41.0"},"reference-count":30,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2018,6,8]],"date-time":"2018-06-08T00:00:00Z","timestamp":1528416000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Distrib Parallel Databases"],"published-print":{"date-parts":[[2019,9]]},"DOI":"10.1007\/s10619-018-7229-1","type":"journal-article","created":{"date-parts":[[2018,6,8]],"date-time":"2018-06-08T15:20:14Z","timestamp":1528471214000},"page":"329-350","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":15,"title":["Scalable machine learning computing a data summarization matrix with a parallel array DBMS"],"prefix":"10.1007","volume":"37","author":[{"given":"Carlos","family":"Ordonez","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yiqun","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"S. Lennart","family":"Johnsson","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,6,8]]},"reference":[{"issue":"4","key":"7229_CR1","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1145\/1721654.1721672","volume":"53","author":"M Armbrust","year":"2010","unstructured":"Armbrust, M., Fox, A., Griffith, R., Joseph, A.D., Katz, R.H., Konwinski, A., Lee, G., Patterson, D.A., Rabkin, A., Stoica, I., Zaharia, M.: A view of cloud computing. Commun. ACM 53(4), 50\u201358 (2010)","journal-title":"Commun. ACM"},{"issue":"3","key":"7229_CR2","doi-asserted-by":"publisher","first-page":"185","DOI":"10.1007\/s10619-011-7082-y","volume":"29","author":"A Behm","year":"2011","unstructured":"Behm, A., Borkar, V.R., Carey, M.J., Grover, R., Li, C., Onose, N., Vernica, R., Deutsch, A., Papakonstantinou, Y., Tsotras, V.J.: ASTERIX: towards a scalable, semistructured data platform for evolving-world models. Distrib. Parallel Databases (DAPD) 29(3), 185\u2013216 (2011)","journal-title":"Distrib. Parallel Databases (DAPD)"},{"key":"7229_CR3","unstructured":"Bradley, P., Fayyad, U., Reina, C.: Scaling clustering algorithms to large databases. In: Proc. ACM KDD Conference, pp. 9\u201315 (1998)"},{"key":"7229_CR4","doi-asserted-by":"publisher","first-page":"256","DOI":"10.1007\/978-3-642-03730-6_21","volume":"5691","author":"Q Chen","year":"2009","unstructured":"Chen, Q., Hsu, M., Liu, R.: Extend udf technology for integrated analytics. Data Warehous. Knowl. Discov. 5691, 256\u2013270 (2009)","journal-title":"Data Warehous. Knowl. Discov."},{"key":"7229_CR5","doi-asserted-by":"crossref","unstructured":"Cormode, G.: Compact summaries over large datasets. In: Proc. ACM PODS (2015)","DOI":"10.1145\/2745754.2745781"},{"key":"7229_CR6","doi-asserted-by":"crossref","unstructured":"Das, S., Sismanis, Y., Beyer, K.S., Gemulla, R., Haas, P.J., McPherson, J.: RICARDO: integrating R and hadoop. In: Proc. ACM SIGMOD Conference, pp. 987\u2013998 (2010)","DOI":"10.1145\/1807167.1807275"},{"issue":"1","key":"7229_CR7","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1145\/1327452.1327492","volume":"51","author":"J Dean","year":"2008","unstructured":"Dean, J., Ghemawat, S.: MapReduce: simplified data processing on large clusters. Commun. ACM 51(1), 107\u2013113 (2008)","journal-title":"Commun. ACM"},{"key":"7229_CR8","doi-asserted-by":"crossref","unstructured":"DuMouchel, W., Volinski, C., Johnson, T., Pregybon, D.: Squashing flat files flatter. In: Proc. ACM KDD Conference (1999)","DOI":"10.1145\/312129.312184"},{"key":"7229_CR9","doi-asserted-by":"crossref","unstructured":"Gemulla, R., Nijkamp, E., Haas, P.J., Sismanis, Y.: Large-scale matrix factorization with distributed stochastic gradient descent. In: Proc. KDD, pp. 69\u201377 (2011)","DOI":"10.1145\/2020408.2020426"},{"key":"7229_CR10","doi-asserted-by":"crossref","unstructured":"Gucht, D.V., Williams, R., Woodruff, D.P., Zhang, Q.: The communication complexity of distributed set-joins with applications to matrix multiplication. In: Proc. ACM PODS, pp. 199\u2013212 (2015)","DOI":"10.1145\/2745754.2745779"},{"key":"7229_CR11","doi-asserted-by":"crossref","unstructured":"Hameurlain, A., Morvan, F.: Parallel relational database systems: why, how and beyond. In: Proc. DEXA Conference, pp. 302\u2013312 (1996)","DOI":"10.1007\/BFb0034690"},{"issue":"4","key":"7229_CR12","doi-asserted-by":"publisher","first-page":"525","DOI":"10.1016\/S0167-8191(02)00074-1","volume":"28","author":"A Hameurlain","year":"2002","unstructured":"Hameurlain, A., Morvan, F.: CPU and incremental memory allocation in dynamic parallelization of SQL queries. Parallel Comput. 28(4), 525\u2013556 (2002)","journal-title":"Parallel Comput."},{"key":"7229_CR13","volume-title":"Data Mining: Concepts and Techniques","author":"J Han","year":"2006","unstructured":"Han, J., Kamber, M.: Data Mining: Concepts and Techniques, 2nd edn. Morgan Kaufmann, San Francisco (2006)","edition":"2"},{"key":"7229_CR14","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-21606-5","volume-title":"The Elements of Statistical Learning","author":"T Hastie","year":"2001","unstructured":"Hastie, T., Tibshirani, R., Friedman, J.H.: The Elements of Statistical Learning, 1st edn. Springer, New York (2001)","edition":"1"},{"issue":"12","key":"7229_CR15","doi-asserted-by":"publisher","first-page":"1700","DOI":"10.14778\/2367502.2367510","volume":"5","author":"J Hellerstein","year":"2012","unstructured":"Hellerstein, J., Re, C., Schoppmann, F., Wang, D.Z., Fratkin, E., Gorajek, A., Ng, K.S., Welton, C.: The MADlib analytics library or MAD skills, the SQL. Proc. VLDB 5(12), 1700\u20131711 (2012)","journal-title":"Proc. VLDB"},{"issue":"12","key":"7229_CR16","first-page":"1790","volume":"5","author":"A Lamb","year":"2012","unstructured":"Lamb, A., Fuller, M., Varadarajan, R., Tran, N., Vandier, B., Doshi, L., Bear, C.: The Vertica analytic database: C-store 7 years later. PVLDB 5(12), 1790\u20131801 (2012)","journal-title":"PVLDB"},{"issue":"3","key":"7229_CR17","doi-asserted-by":"publisher","first-page":"313","DOI":"10.1007\/s10619-014-7145-y","volume":"32","author":"F Li","year":"2014","unstructured":"Li, F., Nath, S.: Scalable data summarization on big data. Distrib. Parallel Databases 32(3), 313\u2013314 (2014)","journal-title":"Distrib. Parallel Databases"},{"issue":"1","key":"7229_CR18","first-page":"285","volume":"16","author":"J Liu","year":"2015","unstructured":"Liu, J., Wright, S.J., Re, C., Bittorf, V., Sridhar, S.: An asynchronous parallel stochastic coordinate descent algorithm. J. Mach. Learn. Res. 16(1), 285\u2013322 (2015)","journal-title":"J. Mach. Learn. Res."},{"issue":"12","key":"7229_CR19","doi-asserted-by":"publisher","first-page":"1752","DOI":"10.1109\/TKDE.2010.44","volume":"22","author":"C Ordonez","year":"2010","unstructured":"Ordonez, C.: Statistical model computation with UDFs. IEEE Trans. Knowl. Data Eng. (TKDE) 22(12), 1752\u20131765 (2010)","journal-title":"IEEE Trans. Knowl. Data Eng. (TKDE)"},{"issue":"3","key":"7229_CR20","doi-asserted-by":"publisher","first-page":"377","DOI":"10.1007\/s10619-013-7134-6","volume":"32","author":"C Ordonez","year":"2014","unstructured":"Ordonez, C., Mohanam, N., Garcia-Alvarado, C.: PCA for large data sets with parallel data summarization. Distrib. Parallel Databases 32(3), 377\u2013403 (2014)","journal-title":"Distrib. Parallel Databases"},{"issue":"7","key":"7229_CR21","doi-asserted-by":"publisher","first-page":"1906","DOI":"10.1109\/TKDE.2016.2545664","volume":"28","author":"C Ordonez","year":"2016","unstructured":"Ordonez, C., Zhang, Y., Cabrera, W.: The Gamma matrix to summarize dense and sparse data sets for big data analytics. IEEE Trans. Knowl. Data Eng. (TKDE) 28(7), 1906\u20131918 (2016)","journal-title":"IEEE Trans. Knowl. Data Eng. (TKDE)"},{"issue":"2","key":"7229_CR22","doi-asserted-by":"publisher","first-page":"129","DOI":"10.1023\/A:1013936118506","volume":"11","author":"S Parthasarathy","year":"2002","unstructured":"Parthasarathy, S., Dwarkadas, S.: Shared state for distributed interactive data mining applications. Distrib. Parallel Databases 11(2), 129\u2013155 (2002)","journal-title":"Distrib. Parallel Databases"},{"issue":"1","key":"7229_CR23","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1145\/1629175.1629197","volume":"53","author":"M Stonebraker","year":"2010","unstructured":"Stonebraker, M., Abadi, D., DeWitt, D.J., Madden, S., Paulson, E., Pavlo, A., Rasin, A.: MapReduce and parallel DBMSs: friends or foes? Commun. ACM 53(1), 64\u201371 (2010)","journal-title":"Commun. ACM"},{"key":"7229_CR24","unstructured":"Stonebraker, M., Becla, J., DeWitt, D.J., Lim, K.T., Maier, D., Ratzesberger, O., Zdonik, S.B.: Requirements for science data bases and SciDB. In: Proc. CIDR Conference (2009)"},{"issue":"3","key":"7229_CR25","doi-asserted-by":"publisher","first-page":"54","DOI":"10.1109\/MCSE.2013.19","volume":"15","author":"M Stonebraker","year":"2013","unstructured":"Stonebraker, M., Brown, P., Zhang, D., Becla, J.: SciDB: a database management system for applications with complex analytics. Comput. Sci. Eng. 15(3), 54\u201362 (2013)","journal-title":"Comput. Sci. Eng."},{"key":"7229_CR26","unstructured":"Stonebraker, M., Madden, S., Abadi, D.\u00a0J., Harizopoulos, S., Hachem, N., Helland, P.: The end of an architectural era: (it\u2019s time for a complete rewrite). In: VLDB, pp. 1150\u20131160 (2007)"},{"key":"7229_CR27","unstructured":"Zaharia, M., Chowdhury, M., Franklin, M.J., Shenker, S., Stoica, I.: Spark: Cluster computing with working sets. In: HotCloud USENIX Workshop (2010)"},{"key":"7229_CR28","doi-asserted-by":"crossref","unstructured":"Zhang, T., Ramakrishnan, R., Livny, M.: BIRCH: An efficient data clustering method for very large databases. In: Proc. ACM SIGMOD Conference, pp. 103\u2013114 (1996)","DOI":"10.1145\/235968.233324"},{"key":"7229_CR29","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Ordonez, C., Cabrera, W.: Big data analytics integrating a parallel columnar DBMS and the R language. In: Proc. of IEEE CCGrid Conference (2016)","DOI":"10.1109\/CCGrid.2016.94"},{"key":"7229_CR30","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Ordonez, C., Johnsson, L.: A cloud system for machine learning exploiting a parallel array DBMS. In: Proc. DEXA Workshops (BDMICS), pp. 22\u201326 (2017)","DOI":"10.1109\/DEXA.2017.21"}],"container-title":["Distributed and Parallel Databases"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10619-018-7229-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10619-018-7229-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10619-018-7229-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,5]],"date-time":"2025-07-05T01:37:16Z","timestamp":1751679436000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10619-018-7229-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,6,8]]},"references-count":30,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2019,9]]}},"alternative-id":["7229"],"URL":"https:\/\/doi.org\/10.1007\/s10619-018-7229-1","relation":{},"ISSN":["0926-8782","1573-7578"],"issn-type":[{"type":"print","value":"0926-8782"},{"type":"electronic","value":"1573-7578"}],"subject":[],"published":{"date-parts":[[2018,6,8]]},"assertion":[{"value":"8 June 2018","order":1,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}