{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,15]],"date-time":"2026-10-15T07:03:45Z","timestamp":1792047825837,"version":"4.4.0"},"reference-count":66,"publisher":"Oxford University Press (OUP)","issue":"2","license":[{"start":{"date-parts":[[2023,2,20]],"date-time":"2023-02-20T00:00:00Z","timestamp":1676851200000},"content-version":"vor","delay-in-days":1464,"URL":"https:\/\/academic.oup.com\/journals\/pages\/open_access\/funder_policies\/chorus\/standard_publication_model"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["DMS-1712872"],"award-info":[{"award-number":["DMS-1712872"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019,4,1]]},"abstract":"<jats:title>Summary<\/jats:title><jats:p>A growing number of generative statistical models do not permit the numerical evaluation of their likelihood functions. Approximate Bayesian computation has become a popular approach to overcome this issue, in which one simulates synthetic data sets given parameters and compares summaries of these data sets with the corresponding observed values. We propose to avoid the use of summaries and the ensuing loss of information by instead using the Wasserstein distance between the empirical distributions of the observed and synthetic data. This generalizes the well-known approach of using order statistics within approximate Bayesian computation to arbitrary dimensions. We describe how recently developed approximations of the Wasserstein distance allow the method to scale to realistic data sizes, and we propose a new distance based on the Hilbert space filling curve. We provide a theoretical study of the method proposed, describing consistency as the threshold goes to 0 while the observations are kept fixed, and concentration properties as the number of observations grows. Various extensions to time series data are discussed. The approach is illustrated on various examples, including univariate and multivariate g-and-k distributions, a toggle switch model from systems biology, a queuing model and a L\u00e9vy-driven stochastic volatility model.<\/jats:p>","DOI":"10.1111\/rssb.12312","type":"journal-article","created":{"date-parts":[[2019,2,18]],"date-time":"2019-02-18T05:35:16Z","timestamp":1550468116000},"page":"235-269","source":"Crossref","is-referenced-by-count":105,"title":["Approximate Bayesian Computation with the Wasserstein Distance"],"prefix":"10.1093","volume":"81","author":[{"given":"Espen","family":"Bernton","sequence":"first","affiliation":[{"name":"Harvard University , Cambridge , USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pierre E.","family":"Jacob","sequence":"additional","affiliation":[{"name":"Harvard University , Cambridge , USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mathieu","family":"Gerber","sequence":"additional","affiliation":[{"name":"University of Bristol \u00a0 UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christian P.","family":"Robert","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2019,2,17]]},"reference":[{"key":"2023022101111891300_","doi-asserted-by":"crossref","first-page":"269","DOI":"10.1111\/j.1467-9868.2009.00736.x","article-title":"Particle Markov chain Monte Carlo methods (with discussion)","volume":"72","author":"Andrieu","year":"2010","journal-title":"J. R. Statist. Soc."},{"key":"2023022101111891300_","doi-asserted-by":"crossref","first-page":"253","DOI":"10.1111\/1467-9868.00336","article-title":"Econometric analysis of realized volatility and its use in estimating stochastic volatility models","volume":"64","author":"Barndorff-Nielsen","year":"2002","journal-title":"J. R. Statist. Soc."},{"key":"2023022101111891300_","volume-title":") Central limit theorems for empirical transportation","author":"del Barrio","year":"2017"},{"key":"2023022101111891300_","doi-asserted-by":"crossref","first-page":"1298","DOI":"10.1016\/j.spl.2006.02.001","article-title":"On minimum Kantorovich distance estimators","volume":"76","author":"Bassetti","year":"2006","journal-title":"Statist. Probab. Lett."},{"key":"2023022101111891300_","doi-asserted-by":"crossref","DOI":"10.1201\/b10956","volume-title":"Statistical Inference: the Minimum Distance Approach","author":"Basu","year":"2011"},{"key":"2023022101111891300_","doi-asserted-by":"crossref","first-page":"2025","DOI":"10.1093\/genetics\/162.4.2025","article-title":"Approximate Bayesian computation in population genetics","volume":"162","author":"Beaumont","year":"2002","journal-title":"Genetics"},{"key":"2023022101111891300_","first-page":"359","volume-title":"Using dynamic time warping to find patterns in time series","author":"Berndt","year":"1994"},{"key":"2023022101111891300_","volume-title":"Inference in generative models using the Wasserstein distance","author":"Bernton","year":"2017"},{"key":"2023022101111891300_","first-page":"171","article-title":"Sequential Monte Carlo with adaptive weights for approximate Bayesian computation","volume":"10","author":"Bonassi","year":"2015","journal-title":"Baysn Anal."},{"key":"2023022101111891300_","doi-asserted-by":"crossref","DOI":"10.2202\/1544-6115.1684","article-title":"Bayesian learning from marginal data in bionetwork models","volume":"10","author":"Bonassi","year":"2011","journal-title":"Statist. Appl. Genet. Molec. Biol."},{"key":"2023022101111891300_","doi-asserted-by":"crossref","first-page":"22","DOI":"10.1007\/s10851-014-0506-3","article-title":"Sliced and Radon Wasserstein barycenters of measures","volume":"51","author":"Bonneel","year":"2015","journal-title":"J. Math. Imgng Visn"},{"key":"2023022101111891300_","doi-asserted-by":"crossref","first-page":"2","DOI":"10.1016\/j.comgeo.2007.08.003","article-title":"Computing the Fr\u00e9chet distance between simple polygons","volume":"41","author":"Buchin","year":"2008","journal-title":"Computnl Geom."},{"key":"2023022101111891300_","doi-asserted-by":"crossref","DOI":"10.1137\/1.9780898717754","volume-title":"Assignment Problems","author":"Burkard","year":"2009"},{"key":"2023022101111891300_","volume-title":"CGAL: User and Reference Manual","author":"CGAL Project","year":"2016"},{"key":"2023022101111891300_","doi-asserted-by":"crossref","first-page":"397","DOI":"10.1111\/j.1467-9868.2012.01046.x","article-title":"SMC2: an efficient algorithm for sequential analysis of state space models","volume":"75","author":"Chopin","year":"2013","journal-title":"J. R. Statist. Soc."},{"key":"2023022101111891300_","first-page":"2292","volume-title":"Sinkhorn distances: lightspeed computation of optimal transport","author":"Cuturi","year":"2013"},{"key":"2023022101111891300_","doi-asserted-by":"crossref","first-page":"1009","DOI":"10.1007\/s11222-011-9271-y","article-title":"An adaptive sequential Monte Carlo method for approximate Bayesian computation","volume":"22","author":"Del Moral","year":"2012","journal-title":"Statist. Comput."},{"key":"2023022101111891300_","doi-asserted-by":"crossref","first-page":"2541","DOI":"10.1016\/j.csda.2011.03.019","article-title":"Likelihood-free Bayesian estimation of multivariate quantile distributions","volume":"55","author":"Drovandi","year":"2011","journal-title":"Computnl Statist. Data Anal."},{"key":"2023022101111891300_","doi-asserted-by":"crossref","first-page":"419","DOI":"10.1111\/j.1467-9868.2011.01010.x","article-title":"Constructing summary statistics for approximate Bayesian computation: semi-automatic approximate Bayesian computation (with discussion)","volume":"74","author":"Fearnhead","year":"2012","journal-title":"J. R. Statist. Soc."},{"key":"2023022101111891300_","doi-asserted-by":"crossref","first-page":"87","DOI":"10.1515\/sagmb-2012-0069","article-title":"On optimality of kernels for approximate Bayesian computation using sequential Monte Carlo","volume":"12","author":"Filippi","year":"2013","journal-title":"Statist. Appl. Genet. Molec. Biol."},{"key":"2023022101111891300_","doi-asserted-by":"crossref","first-page":"707","DOI":"10.1007\/s00440-014-0583-7","article-title":"On the rate of convergence in Wasserstein distance of the empirical measure","volume":"162","author":"Fournier","year":"2015","journal-title":"Probab. Theory Reltd Flds"},{"key":"2023022101111891300_","doi-asserted-by":"crossref","first-page":"593","DOI":"10.1093\/biomet\/asy027","article-title":"Asymptotic properties of approximate Bayesian computation","volume":"105","author":"Frazier","year":"2018","journal-title":"Biometrika"},{"key":"2023022101111891300_","first-page":"1608","volume-title":"Learning generative models with Sinkhorn divergences","author":"Genevay","year":"2017"},{"key":"2023022101111891300_","doi-asserted-by":"crossref","first-page":"509","DOI":"10.1111\/rssb.12104","article-title":"Sequential quasi-Monte Carlo (with discussion)","volume":"77","author":"Gerber","year":"2015","journal-title":"J. R. Statist. Soc."},{"key":"2023022101111891300_","doi-asserted-by":"crossref","DOI":"10.1214\/18-AOS1746","article-title":"Negative association, ordering and convergence of resampling methods","author":"Gerber","year":"2019","journal-title":"Ann. Statist"},{"key":"2023022101111891300_","doi-asserted-by":"crossref","first-page":"e110214","DOI":"10.1371\/journal.pone.0110214","article-title":"The shortlist method for fast computation of the earth mover\u2019s distance and finding optimal solutions to transportation problems","volume":"9","author":"Gottschlich","year":"2014","journal-title":"PLOS One"},{"key":"2023022101111891300_","first-page":"499","volume-title":"Artificial Intelligence and Statistics","author":"Graham","year":"2017"},{"key":"2023022101111891300_","first-page":"1711","volume-title":"Proc. 21st Int. Conf. Artificial Intelligence and Statistics","author":"Jiang","year":"2018"},{"key":"2023022101111891300_","volume-title":"Nonlinear Time Series Analysis","author":"Kantz","year":"2004"},{"key":"2023022101111891300_","first-page":"304","volume-title":"Proc. Winter Simulation Conf. (ed. O. Rose)","author":"Lee","year":"2012"},{"key":"2023022101111891300_","doi-asserted-by":"crossref","first-page":"655","DOI":"10.1093\/biomet\/asu027","article-title":"Variance bounding and geometric ergodicity of Markov chain Monte Carlo kernels for approximate Bayesian computation","volume":"101","author":"Lee","year":"2014","journal-title":"Biometrika"},{"key":"2023022101111891300_","doi-asserted-by":"crossref","first-page":"285","DOI":"10.1093\/biomet\/asx078","article-title":"On the asymptotic efficiency of approximate Bayesian computation estimators","volume":"105","author":"Li","year":"2018","journal-title":"Biometrika"},{"key":"2023022101111891300_","first-page":"199","volume-title":"Proc. 18th Int. Conf. Hybrid Systems: Computation and Control","author":"Majumdar","year":"2015"},{"key":"2023022101111891300_","doi-asserted-by":"crossref","first-page":"1167","DOI":"10.1007\/s11222-011-9288-2","article-title":"Approximate Bayesian computational methods","volume":"22","author":"Marin","year":"2012","journal-title":"Statist. Comput."},{"key":"2023022101111891300_","doi-asserted-by":"crossref","first-page":"1321","DOI":"10.1073\/pnas.1208827110","article-title":"Bayesian computation via empirical likelihood","volume":"110","author":"Mengersen","year":"2013","journal-title":"Proc. Natn. Acad. Sci. USA"},{"key":"2023022101111891300_","doi-asserted-by":"crossref","first-page":"1583","DOI":"10.1111\/j.1467-8659.2011.02032.x","article-title":"A multiscale approach to optimal transport","volume":"30","author":"M\u00e9rigot","year":"2011","journal-title":"Comput. Graph. Forum"},{"key":"2023022101111891300_","article-title":"Robust Bayesian inference via coarsening","author":"Miller","year":"2018","journal-title":"J. Am. Statist. Ass."},{"key":"2023022101111891300_","first-page":"187","article-title":"Measuring the distance between time series","volume":"102","author":"Moeckel","year":"1997","journal-title":"Physica"},{"key":"2023022101111891300_","doi-asserted-by":"crossref","first-page":"1805","DOI":"10.3982\/ECTA9097","article-title":"Risk of Bayesian inference in misspecified models, and the sandwich covariance matrix","volume":"81","author":"M\u00fcller","year":"2013","journal-title":"Econometrica"},{"key":"2023022101111891300_","doi-asserted-by":"crossref","first-page":"494","DOI":"10.1137\/130915376","article-title":"On disturbance state-space models and the particle marginal Metropolis-Hastings sampler","volume":"1","author":"Murray","year":"2013","journal-title":"J. Uncertnty Quantificn"},{"key":"2023022101111891300_","first-page":"45","article-title":"Wasserstein distances in the analysis of time series and dynamical systems","volume":"240","author":"Muskulus","year":"2011","journal-title":"Physica"},{"key":"2023022101111891300_","doi-asserted-by":"crossref","first-page":"189","DOI":"10.32614\/RJ-2015-030","article-title":"abctools: an R package for tuning approximate Bayesian computation analyses","volume":"7","author":"Nunes","year":"2015","journal-title":"R J."},{"key":"2023022101111891300_","article-title":"Statistical aspects of Wasserstein distances","author":"Panaretos","year":"2018","journal-title":"A. Rev. Statist. Appl."},{"key":"2023022101111891300_","first-page":"398","volume-title":"Proc. 19th Int. Conf. Artificial Intelligence and Statistics","author":"Park","year":"2016"},{"key":"2023022101111891300_","article-title":"Computational optimal transport","author":"Peyr\u00e9","year":"2018","journal-title":"Foundns Trends Mach. Learn."},{"key":"2023022101111891300_","volume-title":"A rare event approach to high dimensional approximate Bayesian computation","author":"Prangle","year":"2016"},{"key":"2023022101111891300_","doi-asserted-by":"crossref","first-page":"132","DOI":"10.1016\/j.jmaa.2017.02.003","article-title":"An algorithm to approximate the optimal expected inner product of two vectors with given marginals","volume":"451","author":"Puccetti","year":"2017","journal-title":"J. Math. Anal. Appl."},{"key":"2023022101111891300_","first-page":"435","volume-title":"Proc. Int. Conf. Scale Space and Variational Methods in Computer Vision","author":"Rabin","year":"2011"},{"key":"2023022101111891300_","doi-asserted-by":"crossref","DOI":"10.3390\/e19020047","article-title":"On Wasserstein two-sample testing and related families of nonparametric tests","volume":"19","author":"Ramdas","year":"2017","journal-title":"Entropy"},{"key":"2023022101111891300_","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1023\/A:1013120305780","article-title":"Numerical maximum likelihood estimation for the g-and-k and generalized g-and-h distributions","volume":"12","author":"Rayner","year":"2002","journal-title":"Statist. Comput."},{"key":"2023022101111891300_","doi-asserted-by":"crossref","first-page":"1632","DOI":"10.1214\/13-EJS819","article-title":"A simple approach to maximum intractable likelihood estimation","volume":"7","author":"Rubio","year":"2013","journal-title":"Electron. J. Statist."},{"key":"2023022101111891300_","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4612-0871-6","volume-title":"Space-filling Curves","author":"Sagan","year":"1994"},{"key":"2023022101111891300_","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-20828-2","volume-title":"Optimal Transport for Applied Mathematicians","author":"Santambrogio","year":"2015"},{"key":"2023022101111891300_","doi-asserted-by":"crossref","first-page":"531","DOI":"10.1007\/978-3-319-33507-0_28","volume-title":"Monte Carlo and Quasi-Monte Carlo Methods","author":"Schretter","year":"2016"},{"key":"2023022101111891300_","volume-title":"transport: optimal transport in various forms","author":"Schuhmacher","year":"2017"},{"key":"2023022101111891300_","volume-title":"On Bayesian inference for the M\/G\/1 queue with efficient MCMC sampling","author":"Shestopaloff","year":"2014"},{"key":"2023022101111891300_","doi-asserted-by":"crossref","first-page":"87","DOI":"10.1201\/9781315117195-4","volume-title":"Handbook of Approximate Bayesian Computation","author":"Sisson","year":"2018"},{"key":"2023022101111891300_","doi-asserted-by":"crossref","first-page":"219","DOI":"10.1111\/rssb.12236","article-title":"Inference for empirical Wasserstein distances on finite spaces","volume":"80","author":"Sommerfeld","year":"2018","journal-title":"J. R. Statist. Soc."},{"key":"2023022101111891300_","doi-asserted-by":"crossref","first-page":"1507","DOI":"10.1534\/genetics.108.098129","article-title":"Approximate Bayesian computation without summary statistics: the case of admixture","volume":"181","author":"Sousa","year":"2009","journal-title":"Genetics"},{"key":"2023022101111891300_","first-page":"912","volume-title":"Artificial Intelligence and Statistics","author":"Srivastava","year":"2015"},{"key":"2023022101111891300_","doi-asserted-by":"crossref","first-page":"519","DOI":"10.1007\/s00332-003-0534-4","article-title":"Delay embeddings for forced system: II, Stochastic forcing","volume":"13","author":"Stark","year":"2003","journal-title":"J. Nonlin. Sci."},{"key":"2023022101111891300_","doi-asserted-by":"crossref","first-page":"919","DOI":"10.1214\/aop\/1176988735","article-title":"The transportation cost from the uniform measure to the empirical measure in dimension 3","volume":"22","author":"Talagrand","year":"1994","journal-title":"Ann. Probab."},{"key":"2023022101111891300_","doi-asserted-by":"crossref","first-page":"187","DOI":"10.1007\/s10851-017-0726-4","article-title":"A transportation lp distance for signal analysis","volume":"59","author":"Thorpe","year":"2017","journal-title":"J. Math. Imgng Visn"},{"key":"2023022101111891300_","doi-asserted-by":"crossref","DOI":"10.1090\/gsm\/058","volume-title":"Topics in Optimal Transportation","author":"Villani","year":"2003"},{"key":"2023022101111891300_","volume-title":"Optimal Transport, Old and New","author":"Villani","year":"2008"},{"key":"2023022101111891300_","volume-title":"Sharp asymptotic and finite-sample rates of convergence of empirical measures in Wasserstein distance","author":"Weed","year":"2017"}],"container-title":["Journal of the Royal Statistical Society Series B: Statistical Methodology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.wiley.com\/onlinelibrary\/tdm\/v1\/articles\/10.1111%2Frssb.12312","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/rssb.12312","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1111\/rssb.12312","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/am-pdf\/10.1111\/rssb.12312","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jrsssb\/article-pdf\/81\/2\/235\/49273594\/jrsssb_81_2_235.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jrsssb\/article-pdf\/81\/2\/235\/49273594\/jrsssb_81_2_235.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,13]],"date-time":"2023-09-13T18:32:15Z","timestamp":1694629935000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jrsssb\/article\/81\/2\/235\/7048431"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,2,17]]},"references-count":66,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2019,2,17]]},"published-print":{"date-parts":[[2019,4,1]]}},"URL":"https:\/\/doi.org\/10.1111\/rssb.12312","relation":{},"ISSN":["1369-7412","1467-9868"],"issn-type":[{"value":"1369-7412","type":"print"},{"value":"1467-9868","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2019,4]]},"published":{"date-parts":[[2019,2,17]]}}}