{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T08:43:35Z","timestamp":1790757815592,"version":"4.1.0"},"reference-count":44,"publisher":"Oxford University Press (OUP)","issue":"3","license":[{"start":{"date-parts":[[2023,1,19]],"date-time":"2023-01-19T00:00:00Z","timestamp":1674086400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/journals\/pages\/open_access\/funder_policies\/chorus\/standard_publication_model"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,8,14]]},"abstract":"<jats:title>Summary<\/jats:title><jats:p>Loss-based clustering methods, such as k-means clustering and its variants, are standard tools for finding groups in data. However, the lack of quantification of uncertainty in the estimated clusters is a disadvantage. Model-based clustering based on mixture models provides an alternative approach, but such methods face computational problems and are highly sensitive to the choice of kernel. In this article we propose a generalized Bayes framework that bridges between these paradigms through the use of Gibbs posteriors. In conducting Bayesian updating, the loglikelihood is replaced by a loss function for clustering, leading to a rich family of clustering methods. The Gibbs posterior represents a coherent updating of Bayesian beliefs without needing to specify a likelihood for the data, and can be used for characterizing uncertainty in clustering. We consider losses based on Bregman divergence and pairwise similarities, and develop efficient deterministic algorithms for point estimation along with sampling algorithms for uncertainty quantification. Several existing clustering algorithms, including k-means, can be interpreted as generalized Bayes estimators in our framework, and thus we provide a method of uncertainty quantification for these approaches, allowing, for example, calculation of the probability that a data point is well clustered.<\/jats:p>","DOI":"10.1093\/biomet\/asad004","type":"journal-article","created":{"date-parts":[[2023,1,18]],"date-time":"2023-01-18T20:33:41Z","timestamp":1674074021000},"page":"559-578","source":"Crossref","is-referenced-by-count":13,"title":["A generalized Bayes framework for probabilistic clustering"],"prefix":"10.1093","volume":"110","author":[{"given":"Tommaso","family":"Rigon","sequence":"first","affiliation":[{"name":"University of Milano\u2013Bicocca Department of Economics, Management and Statistics, , Piazza dell\u2019Ateneo Nuovo 1, 20126 Milano, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Amy H","family":"Herring","sequence":"additional","affiliation":[{"name":"Duke University Department of Statistical Science, , Box 90251, Durham, North Carolina 27708, U.S.A"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David B","family":"Dunson","sequence":"additional","affiliation":[{"name":"Duke University Department of Statistical Science, , Box 90251, Durham, North Carolina 27708, U.S.A"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2023,1,19]]},"reference":[{"key":"2023081420144643800_B1","doi-asserted-by":"crossref","DOI":"10.1002\/0471249688","volume-title":"Categorical Data Analysis","author":"Agresti,","year":"2002"},{"key":"2023081420144643800_B2","first-page":"1705","article-title":"Clustering with Bregman divergences","volume":"6","author":"Banerjee,","year":"2005","journal-title":"J. Mach. Learn. Res."},{"key":"2023081420144643800_B3","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1007\/s00357-008-9002-z","article-title":"Probabilistic D-clustering","volume":"25","author":"Ben-israel,","year":"2008","journal-title":"J. Classif."},{"key":"2023081420144643800_B4","doi-asserted-by":"crossref","first-page":"1103","DOI":"10.1111\/rssb.12158","article-title":"A general framework for updating belief distributions","volume":"78","author":"Bissiri,","year":"2016","journal-title":"J. R. Statist. Soc. B"},{"key":"2023081420144643800_B5","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1016\/0167-9473(96)88919-5","article-title":"Probabilistic models in cluster analysis","volume":"23","author":"Bock,","year":"1996","journal-title":"Comp. Statist. Data Anal."},{"key":"2023081420144643800_B6","first-page":"226","article-title":"MAD-Bayes: MAP-based asymptotic derivation from Bayes","volume-title":"Proc. 30th Int. Conf. Machine Learning","author":"Broderick,","year":"2013"},{"key":"2023081420144643800_B7","doi-asserted-by":"crossref","first-page":"212","DOI":"10.1109\/TPAMI.2013.217","article-title":"Are Gibbs-type priors the most natural generalization of the Dirichlet process?","volume":"37","author":"De Blasi,","year":"2015","journal-title":"IEEE Trans. Pat. Anal. Mach. Intel."},{"key":"2023081420144643800_B8","first-page":"1","article-title":"Bayesian distance clustering","volume":"22","author":"Duan,","year":"2021","journal-title":"J. Mach. Learn. Res."},{"key":"2023081420144643800_B9","doi-asserted-by":"crossref","first-page":"611","DOI":"10.1198\/016214502760047131","article-title":"Model-based clustering, discriminant analysis, and density estimation","volume":"97","author":"Fraley,","year":"2002","journal-title":"J. Am. Statist. Assoc."},{"key":"2023081420144643800_B10","doi-asserted-by":"crossref","first-page":"367","DOI":"10.1214\/09-BA414","article-title":"Improved criteria for clustering based on the posterior similarity matrix","volume":"4","author":"Fritsch,","year":"2009","journal-title":"Bayesian Anal."},{"key":"2023081420144643800_B11","doi-asserted-by":"crossref","DOI":"10.1017\/9781139029834","volume-title":"Fundamentals of Nonparametric Bayesian Inference","author":"Ghosal,","year":"2017"},{"key":"2023081420144643800_B12","article-title":"Coarsened mixtures of hierarchical skew normal kernels for flow cytometry analyses","author":"Gorsky,","year":"2020"},{"key":"2023081420144643800_B13","doi-asserted-by":"crossref","first-page":"1069","DOI":"10.1214\/17-BA1085","article-title":"Inconsistency of Bayesian inference for misspecified linear models, and a proposal for repairing it","volume":"12","author":"Gr\u00fcnwald,","year":"2017","journal-title":"Bayesian Anal."},{"key":"2023081420144643800_B14","doi-asserted-by":"crossref","first-page":"241","DOI":"10.1016\/S0378-3758(96)00129-2","article-title":"$L^p$-norm spherical distribution","volume":"60","author":"Gupta,","year":"1997","journal-title":"J. Statist. Plan. Infer."},{"key":"2023081420144643800_B15","doi-asserted-by":"crossref","first-page":"100","DOI":"10.2307\/2346830","article-title":"Algorithm AS 136: A $K$-means clustering algorithm","volume":"28","author":"Hartigan,","year":"1979","journal-title":"Appl. Statist."},{"key":"2023081420144643800_B16","doi-asserted-by":"crossref","DOI":"10.1201\/b19706","volume-title":"Handbook of Cluster Analysis","author":"Hennig,","year":"2015"},{"key":"2023081420144643800_B17","doi-asserted-by":"crossref","first-page":"4849","DOI":"10.1214\/19-EJS1640","article-title":"Quantile-based clustering","volume":"13","author":"Hennig,","year":"2019","journal-title":"Electron. J. Statist."},{"key":"2023081420144643800_B18","first-page":"497","article-title":"Assigning a value to a power likelihood in a general Bayesian model","volume":"104","author":"Holmes,","year":"2017","journal-title":"Biometrika"},{"key":"2023081420144643800_B19","doi-asserted-by":"crossref","first-page":"651","DOI":"10.1016\/j.patrec.2009.09.011","article-title":"Data clustering: 50 years beyond K-means","volume":"31","author":"Jain,","year":"2010","journal-title":"Pat. Recog. Lett."},{"key":"2023081420144643800_B20","doi-asserted-by":"crossref","first-page":"158","DOI":"10.1198\/1061860043001","article-title":"A split-merge Markov chain Monte Carlo procedure for the Dirichlet process mixture model","volume":"13","author":"Jain,","year":"2004","journal-title":"J. Comp. Graph. Statist."},{"key":"2023081420144643800_B21","doi-asserted-by":"crossref","first-page":"2207","DOI":"10.1214\/07-AOS547","article-title":"Gibbs posterior for variable selection in high-dimensional classification and data-mining","volume":"36","author":"Jiang,","year":"2008","journal-title":"Ann. Statist."},{"key":"2023081420144643800_B22","doi-asserted-by":"crossref","first-page":"127","DOI":"10.1111\/j.2517-6161.1987.tb01685.x","article-title":"Exponential dispersion models","volume":"49","author":"J\u00f8rgensen,","year":"1987","journal-title":"J. R. Statist. Soc. B"},{"key":"2023081420144643800_B23","doi-asserted-by":"crossref","DOI":"10.1002\/9780470316801","volume-title":"Finding Groups in Data: An Introduction to Cluster Analysis","author":"Kaufman,","year":"1990"},{"key":"2023081420144643800_B24","first-page":"1131","article-title":"Revisiting k-means: New algorithms via Bayesian nonparametrics","volume-title":"Proc. 29th Int. Conf. Machine Learning","author":"Kulis,","year":"2012"},{"key":"2023081420144643800_B25","doi-asserted-by":"crossref","first-page":"526","DOI":"10.1198\/106186007X238855","article-title":"Bayesian model-based clustering procedures","volume":"16","author":"Lau,","year":"2007","journal-title":"J. Comp. Graph. Statist."},{"key":"2023081420144643800_B26","volume-title":"Latent Structure Analysis","author":"Lazarsfeld,","year":"1968"},{"key":"2023081420144643800_B27","doi-asserted-by":"crossref","first-page":"117","DOI":"10.1016\/S0378-3758(01)00215-4","article-title":"A composite likelihood approach to (co)variance components estimation","volume":"103","author":"Lele,","year":"2002","journal-title":"J. Statist. Plan. Infer."},{"key":"2023081420144643800_B28","doi-asserted-by":"crossref","first-page":"891","DOI":"10.1093\/biomet\/asaa030","article-title":"The Pitman\u2013Yor multinomial process for mixture modeling","volume":"107","author":"Lijoi,","year":"2020","journal-title":"Biometrika"},{"key":"2023081420144643800_B29","doi-asserted-by":"crossref","first-page":"129","DOI":"10.1109\/TIT.1982.1056489","article-title":"Least squares quantization in PCM","volume":"28","author":"Lloyd,","year":"1982","journal-title":"IEEE Trans. Info. Theory"},{"key":"2023081420144643800_B30","doi-asserted-by":"crossref","first-page":"465","DOI":"10.1093\/biomet\/asz006","article-title":"General Bayesian updating and the loss-likelihood bootstrap","volume":"106","author":"Lyddon,","year":"2019","journal-title":"Biometrika"},{"key":"2023081420144643800_B31","first-page":"230","article-title":"Some PAC-Bayesian theorems","volume-title":"Proc. 11th Ann. Conf. Computational Learning Theory","author":"McAllester,","year":"1998"},{"key":"2023081420144643800_B32","doi-asserted-by":"crossref","first-page":"873","DOI":"10.1016\/j.jmva.2006.11.013","article-title":"Comparing clusterings\u2014an information based distance","volume":"98","author":"Meil\u0103,","year":"2007","journal-title":"J. Mult. Anal."},{"key":"2023081420144643800_B33","doi-asserted-by":"crossref","first-page":"1113","DOI":"10.1080\/01621459.2018.1469995","article-title":"Robust Bayesian inference via coarsening","volume":"114","author":"Miller,","year":"2019","journal-title":"J. Am. Statist. Assoc."},{"key":"2023081420144643800_B34","doi-asserted-by":"crossref","first-page":"260","DOI":"10.1198\/jcgs.2011.09066","article-title":"A product partition model with regression on covariates","volume":"20","author":"M\u00fcller,","year":"2011","journal-title":"J. Comp. Graph. Statist."},{"key":"2023081420144643800_B35","article-title":"Cohesion and repulsion in Bayesian distance clustering","author":"Natarajan,","year":"2021"},{"key":"2023081420144643800_B36","first-page":"1203","article-title":"Bayesian generalized product partition model","volume":"20","author":"Park,","year":"2010","journal-title":"Statist. Sinica"},{"key":"2023081420144643800_B37","doi-asserted-by":"crossref","first-page":"557","DOI":"10.1111\/1467-9868.00402","article-title":"Bayesian clustering and product partition models","volume":"65","author":"Quintana,","year":"2003","journal-title":"J. R. Statist. Soc. B"},{"key":"2023081420144643800_B38","doi-asserted-by":"crossref","first-page":"24","DOI":"10.1214\/20-STS819","article-title":"The dependent Dirichlet process and related models","volume":"37","author":"Quintana,","year":"2022","journal-title":"Statist. Sci."},{"key":"2023081420144643800_B39","first-page":"2","article-title":"A PAC analysis of a Bayesian estimator","author":"Shawe-Taylor,","year":"1997","journal-title":"Proc. 10th Ann. Conf. Computational Learning Theory"},{"key":"2023081420144643800_B40","doi-asserted-by":"crossref","first-page":"479","DOI":"10.1093\/biomet\/asy054","article-title":"Calibrating general posterior credible regions","volume":"106","author":"Syring,","year":"2019","journal-title":"Biometrika"},{"key":"2023081420144643800_B41","first-page":"5","article-title":"An overview of composite likelihood methods","volume":"21","author":"Varin,","year":"2011","journal-title":"Statist. Sinica"},{"key":"2023081420144643800_B42","doi-asserted-by":"crossref","first-page":"559","DOI":"10.1214\/17-BA1073","article-title":"Bayesian cluster analysis: Point estimation and credible balls","volume":"13","author":"Wade,","year":"2018","journal-title":"Bayesian Anal."},{"key":"2023081420144643800_B43","doi-asserted-by":"crossref","first-page":"196","DOI":"10.1198\/jcgs.2010.07081","article-title":"Fast Bayesian inference in Dirichlet process mixture models","volume":"20","author":"Wang,","year":"2011","journal-title":"J. Comp. Graph. Statist."},{"key":"2023081420144643800_B44","doi-asserted-by":"crossref","first-page":"203","DOI":"10.1007\/s11222-018-9803-9","article-title":"Bayesian nonparametric clustering for large data sets","volume":"29","author":"Zuanetti,","year":"2019","journal-title":"Statist. Comp."}],"container-title":["Biometrika"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/biomet\/advance-article-pdf\/doi\/10.1093\/biomet\/asad004\/49772198\/asad004.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/biomet\/article-pdf\/110\/3\/559\/51111533\/asad004.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/biomet\/article-pdf\/110\/3\/559\/51111533\/asad004.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,12]],"date-time":"2024-10-12T13:06:55Z","timestamp":1728738415000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/biomet\/article\/110\/3\/559\/6992658"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,19]]},"references-count":44,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2023,1,19]]},"published-print":{"date-parts":[[2023,8,14]]}},"URL":"https:\/\/doi.org\/10.1093\/biomet\/asad004","relation":{},"ISSN":["0006-3444","1464-3510"],"issn-type":[{"value":"0006-3444","type":"print"},{"value":"1464-3510","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2023,9,1]]},"published":{"date-parts":[[2023,1,19]]}}}