{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T10:28:10Z","timestamp":1772792890757,"version":"3.50.1"},"reference-count":32,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2018,2,12]],"date-time":"2018-02-12T00:00:00Z","timestamp":1518393600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2018,2,12]],"date-time":"2018-02-12T00:00:00Z","timestamp":1518393600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100002322","name":"Coordena\u00e7\u00e3o de Aperfei\u00e7oamento de Pessoal de N\u00edvel Superior","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002322","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000054","name":"National Cancer Institute","doi-asserted-by":"publisher","award":["132891-07"],"award-info":[{"award-number":["132891-07"]}],"id":[{"id":"10.13039\/100000054","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Stat Comput"],"published-print":{"date-parts":[[2019,3]]},"DOI":"10.1007\/s11222-018-9803-9","type":"journal-article","created":{"date-parts":[[2018,2,12]],"date-time":"2018-02-12T12:01:43Z","timestamp":1518436903000},"page":"203-215","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":14,"title":["Bayesian nonparametric clustering for large data sets"],"prefix":"10.1007","volume":"29","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1591-959X","authenticated-orcid":false,"given":"Daiane Aparecida","family":"Zuanetti","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peter","family":"M\u00fcller","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yitan","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shengjie","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuan","family":"Ji","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,2,12]]},"reference":[{"key":"9803_CR1","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/978-3-319-16238-6_1","volume-title":"Bayesian Statistics from Methods to Models and Applications","author":"J Arbel","year":"2015","unstructured":"Arbel, J., Lijoi, A., Nipoti, B.: Bayesian survival model based on moment characterization. In: Fr\u00fchwirth-Schnatter, S., Bitto, A., Kastner, G., Posekany, A. (eds.) Bayesian Statistics from Methods to Models and Applications, pp. 3\u201314. Springer, Cham (2015)"},{"key":"9803_CR2","doi-asserted-by":"publisher","first-page":"353","DOI":"10.1214\/aos\/1176342372","volume":"1","author":"D Blackwell","year":"1973","unstructured":"Blackwell, D., MacQueen, J.B.: Ferguson distributions via P\u00f3lya urn schemes. Ann. Stat. 1, 353\u2013355 (1973)","journal-title":"Ann. Stat."},{"key":"9803_CR3","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.2017.1294075","author":"A Bouchard-C\u00f4t\u00e9","year":"2017","unstructured":"Bouchard-C\u00f4t\u00e9, A., Vollmer, S.J., Doucet, A.: The bouncy particle sampler: a non-reversible rejection-free Markov chain Monte Carlo method. J. Am. Stat. Assoc. (2017). https:\/\/doi.org\/10.1080\/01621459.2017.1294075","journal-title":"J. Am. Stat. Assoc."},{"issue":"1","key":"9803_CR4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1080\/03610927408827101","volume":"3","author":"T Cali\u0144ski","year":"1974","unstructured":"Cali\u0144ski, T., Harabasz, J.: A dendrite method for cluster analysis. Commun. Stat. Theory Methods 3(1), 1\u201327 (1974)","journal-title":"Commun. Stat. Theory Methods"},{"issue":"4","key":"9803_CR5","doi-asserted-by":"publisher","first-page":"547","DOI":"10.1016\/j.dss.2009.05.016","volume":"47","author":"P Cortez","year":"2009","unstructured":"Cortez, P., Cerdeira, A., Almeida, F., Matos, T., Reis, J.: Modeling wine preferences by data mining from physicochemical properties. Decision Support Syst. 47(4), 547\u2013553 (2009)","journal-title":"Decision Support Syst."},{"key":"9803_CR6","doi-asserted-by":"publisher","first-page":"201","DOI":"10.1017\/CBO9780511584589.011","volume-title":"Bayesian Inference for Gene Expression and Proteomics","author":"DB Dahl","year":"2006","unstructured":"Dahl, D.B.: Model-based clustering for expression data via a Dirichlet process mixture model. In: Vannucci, M., Do, K.A., M\u00fcller, P. (eds.) Bayesian Inference for Gene Expression and Proteomics, pp. 201\u2013218. Cambridge University Press, Cambridge (2006)"},{"key":"9803_CR7","first-page":"226","volume":"96","author":"M Ester","year":"1996","unstructured":"Ester, M., Kriegel, H.P., Sander, J., Xu, X.: A density-based algorithm for discovering clusters in large spatial databases with noise. Knowl. Discov. Databases 96, 226\u2013231 (1996)","journal-title":"Knowl. Discov. Databases"},{"issue":"2","key":"9803_CR8","doi-asserted-by":"publisher","first-page":"179","DOI":"10.1111\/j.1469-1809.1936.tb02137.x","volume":"7","author":"RA Fisher","year":"1936","unstructured":"Fisher, R.A.: The use of multiple measurements in taxonomic problems. Ann. Eugen. 7(2), 179\u2013188 (1936)","journal-title":"Ann. Eugen."},{"issue":"458","key":"9803_CR9","doi-asserted-by":"publisher","first-page":"611","DOI":"10.1198\/016214502760047131","volume":"97","author":"C Fraley","year":"2002","unstructured":"Fraley, C., Raftery, A.E.: Model-based clustering, discriminant analysis, and density estimation. J. Am. Stat. Assoc. 97(458), 611\u2013631 (2002)","journal-title":"J. Am. Stat. Assoc."},{"issue":"2","key":"9803_CR10","doi-asserted-by":"publisher","first-page":"155","DOI":"10.1007\/s00357-007-0004-5","volume":"24","author":"C Fraley","year":"2007","unstructured":"Fraley, C., Raftery, A.E.: Bayesian regularization for normal mixture estimation and model-based clustering. J. Classif. 24(2), 155\u2013181 (2007)","journal-title":"J. Classif."},{"key":"9803_CR11","unstructured":"Ge, H., Chen, Y., Wan, M., Ghahramani, Z.: Distributed inference for Dirichlet process mixture models. In: Bach, F., Blei, D. (eds.) Proceedings of the 32nd International Conference on Machine Learning, Proceedings of Machine Learning Research, vol.\u00a037, pp. 2276\u20132284. PMLR, Lille, France (2015)"},{"key":"9803_CR12","doi-asserted-by":"crossref","first-page":"501","DOI":"10.1111\/j.2517-6161.1994.tb01996.x","volume":"56","author":"AE Gelfand","year":"1994","unstructured":"Gelfand, A.E., Dey, D.K.: Bayesian model choice: asymptotics and exact calculations. J. R. Stat. Soc. Ser. B (Stat. Methodol.) 56, 501\u2013514 (1994)","journal-title":"J. R. Stat. Soc. Ser. B (Stat. Methodol.)"},{"key":"9803_CR13","first-page":"22","volume-title":"Bayesian Nonparametrics","author":"S Ghoshal","year":"2010","unstructured":"Ghoshal, S.: The Dirichlet process, related priors and posterior asymptotics. In: Hjort, N.L., Holmes, C., M\u00fcller, P., Walker, S.G. (eds.) Bayesian Nonparametrics, pp. 22\u201334. Cambridge University Press, Cambridge (2010)"},{"issue":"3","key":"9803_CR14","doi-asserted-by":"publisher","first-page":"515","DOI":"10.1109\/TKDE.2003.1198387","volume":"15","author":"S Guha","year":"2003","unstructured":"Guha, S., Meyerson, A., Mishra, N., Motwani, R., O\u2019Callaghan, L.: Clustering data streams: theory and practice. IEEE Trans. Knowl. Data Eng. 15(3), 515\u2013528 (2003)","journal-title":"IEEE Trans. Knowl. Data Eng."},{"issue":"1","key":"9803_CR15","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/s11634-010-0058-3","volume":"4","author":"C Hennig","year":"2010","unstructured":"Hennig, C.: Methods for merging Gaussian mixture components. Adv. Data Anal. Classif. 4(1), 3\u201334 (2010)","journal-title":"Adv. Data Anal. Classif."},{"key":"9803_CR16","doi-asserted-by":"crossref","unstructured":"Huang, Z., Gelman, A.: Sampling for Bayesian computation with large datasets. Available at SSRN 1010107 (2005)","DOI":"10.2139\/ssrn.1010107"},{"issue":"8","key":"9803_CR17","doi-asserted-by":"publisher","first-page":"651","DOI":"10.1016\/j.patrec.2009.09.011","volume":"31","author":"AK Jain","year":"2010","unstructured":"Jain, A.K.: Data clustering: 50 years beyond k-means. Pattern Recognit. Lett. 31(8), 651\u2013666 (2010)","journal-title":"Pattern Recognit. Lett."},{"key":"9803_CR18","unstructured":"Kulis, B., Jordan, M.I.: Revisiting k-means: new algorithms via Bayesian nonparametrics. In: Langford, J., Pineau, J. (eds.) Proceedings of the 29th International Conference on Machine Learning (ICML-12), pp. 513\u2013520. ACM, New York, NY, USA (2012)"},{"key":"9803_CR19","unstructured":"Lin, D.: Online learning of nonparametric mixture models via sequential variational approximation. In: Proceedings of the 26th International Conference on Neural Information Processing Systems, NIPS\u201913, pp. 395\u2013403. Curran Associates Inc., USA (2013)"},{"issue":"2","key":"9803_CR20","doi-asserted-by":"publisher","first-page":"251","DOI":"10.2307\/3315637","volume":"27","author":"SN MacEachern","year":"1999","unstructured":"MacEachern, S.N., Clyde, M., Liu, J.S.: Sequential importance sampling for nonparametric Bayes models: the next generation. Can. J. Stat. 27(2), 251\u2013267 (1999)","journal-title":"Can. J. Stat."},{"issue":"501","key":"9803_CR21","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1080\/01621459.2012.746058","volume":"108","author":"R Mitra","year":"2013","unstructured":"Mitra, R., M\u00fcller, P., Liang, S., Yue, L., Ji, Y.: A Bayesian graphical model for ChIP-seq data on histone modifications. J. Am. Stat. Assoc. 108(501), 69\u201380 (2013)","journal-title":"J. Am. Stat. Assoc."},{"key":"9803_CR22","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1007\/978-1-4612-1732-9_3","volume-title":"Practical Nonparametric and Semiparametric Bayesian Statistics","author":"MA Newton","year":"1998","unstructured":"Newton, M.A., Quintana, F.A., Zhang, Y.: Nonparametric Bayes methods using predictive updating. In: Dey, D., M\u00fcller, P., Sinha, D. (eds.) Practical Nonparametric and Semiparametric Bayesian Statistics, pp. 45\u201361. Springer, New York (1998)"},{"issue":"4","key":"9803_CR23","doi-asserted-by":"publisher","first-page":"821","DOI":"10.1093\/biostatistics\/kxm008","volume":"8","author":"ML Pennell","year":"2007","unstructured":"Pennell, M.L., Dunson, D.B.: Fitting semiparametric random effects models to large data sets. Biostatistics 8(4), 821\u2013834 (2007)","journal-title":"Biostatistics"},{"key":"9803_CR24","doi-asserted-by":"crossref","first-page":"175","DOI":"10.1111\/j.2517-6161.1990.tb01780.x","volume":"52","author":"L Pettit","year":"1990","unstructured":"Pettit, L.: The conditional predictive ordinate for the normal distribution. J. R. Stat. Soc. Ser. B (Stat. Methodol.) 52, 175\u2013184 (1990)","journal-title":"J. R. Stat. Soc. Ser. B (Stat. Methodol.)"},{"issue":"2","key":"9803_CR25","first-page":"78","volume":"11","author":"SL Scott","year":"2016","unstructured":"Scott, S.L., Blocker, A.W., Bonassi, F.V., Chipman, H.A., George, E.I., McCulloch, R.E.: Bayes and big data: the consensus Monte Carlo algorithm. Int. J. Manag. Sci. Eng. Manag. 11(2), 78\u201388 (2016)","journal-title":"Int. J. Manag. Sci. Eng. Manag."},{"key":"9803_CR26","unstructured":"Tank, A., Foti, N., Fox, E.: Streaming variational inference for Bayesian nonparametric mixture models. In: Lebanon, G., Vishwanathan, S.V.N. (eds.) Proceedings of the Eighteenth International Conference on Artificial Intelligence and Statistics, Proceedings of Machine Learning Research, vol.\u00a038, pp. 968\u2013976. PMLR, San Diego, California, USA (2015)"},{"issue":"4","key":"9803_CR27","doi-asserted-by":"publisher","first-page":"267","DOI":"10.1007\/BF02289263","volume":"18","author":"RL Thorndike","year":"1953","unstructured":"Thorndike, R.L.: Who belongs in the family? Psychometrika 18(4), 267\u2013276 (1953)","journal-title":"Psychometrika"},{"issue":"1","key":"9803_CR28","doi-asserted-by":"publisher","first-page":"196","DOI":"10.1198\/jcgs.2010.07081","volume":"20","author":"L Wang","year":"2011","unstructured":"Wang, L., Dunson, D.B.: Fast Bayesian inference in Dirichlet process mixture models. J. Comput. Graph. Stat. 20(1), 196\u2013216 (2011)","journal-title":"J. Comput. Graph. Stat."},{"key":"9803_CR29","unstructured":"Williamson, S.A., Dubey, A., Xing, E.P.: Parallel Markov chain Monte Carlo for nonparametric mixture models. In: Proceedings of the 30th International Conference on International Conference on Machine Learning, ICML\u201913, vol. 28, pp. I-98\u2013I-106. JMLR.org (2013)"},{"issue":"3","key":"9803_CR30","doi-asserted-by":"publisher","first-page":"645","DOI":"10.1109\/TNN.2005.845141","volume":"16","author":"R Xu","year":"2005","unstructured":"Xu, R., Wunsch, D., et al.: Survey of clustering algorithms. IEEE Trans. Neural Netw. 16(3), 645\u2013678 (2005)","journal-title":"IEEE Trans. Neural Netw."},{"key":"9803_CR31","doi-asserted-by":"crossref","unstructured":"Zhao, W., Ma, H., He, Q.: Parallel k-means clustering based on MapReduce. In: Jaatun, M.G., Zhao, G., Rong, C. (eds.) Cloud Computing, pp. 674\u2013679. Springer, Berlin (2009)","DOI":"10.1007\/978-3-642-10665-1_71"},{"key":"9803_CR32","doi-asserted-by":"crossref","unstructured":"Zhu, Y., Xu, Y., Helseth, D.L., Gulukota, K., Yang, S., Pesce, L.L., Mitra, R., M\u00fcller, P., Sengupta, S., Guo, W., et\u00a0al.: Zodiac: A comprehensive depiction of genetic interactions in cancer by integrating TCGA data. J. Natl. Cancer Inst. 107(8), 1\u20139 (2015)","DOI":"10.1093\/jnci\/djv129"}],"container-title":["Statistics and Computing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11222-018-9803-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11222-018-9803-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11222-018-9803-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T04:02:06Z","timestamp":1719806526000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11222-018-9803-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,2,12]]},"references-count":32,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2019,3]]}},"alternative-id":["9803"],"URL":"https:\/\/doi.org\/10.1007\/s11222-018-9803-9","relation":{},"ISSN":["0960-3174","1573-1375"],"issn-type":[{"value":"0960-3174","type":"print"},{"value":"1573-1375","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,2,12]]},"assertion":[{"value":"21 April 2017","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"31 January 2018","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 February 2018","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}