{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T22:15:45Z","timestamp":1792793745448,"version":"4.5.0"},"reference-count":47,"publisher":"Oxford University Press (OUP)","issue":"2","license":[{"start":{"date-parts":[[2020,2,28]],"date-time":"2020-02-28T00:00:00Z","timestamp":1582848000000},"content-version":"vor","delay-in-days":365,"URL":"https:\/\/academic.oup.com\/journals\/pages\/open_access\/funder_policies\/chorus\/standard_publication_model"}],"funder":[{"name":"Division of Science Research Computing Group at Harvard University","id":[{"id":"https:\/\/ror.org\/03vek6s52","id-type":"ROR","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100008982","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100008982","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000183","name":"Army Research Office","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000183","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019,6,1]]},"abstract":"<jats:title>Summary<\/jats:title>\n                  <jats:p>We propose a method for parallelization of Hamiltonian Monte Carlo estimators. Our approach involves constructing a pair of Hamiltonian Monte Carlo chains that are coupled in such a way that they meet exactly after some random number of iterations. These chains can then be combined so that the resulting estimators are unbiased. This allows us to produce independent replicates in parallel and average them to obtain estimators that are consistent in the limit of the number of replicates, rather than in the usual limit of the number of Markov chain iterations. We investigate the scalability of our coupling in high dimensions on a toy example. The choice of algorithmic parameters and the efficiency of our proposed approach are then illustrated on a logistic regression with 300 covariates and a log-Gaussian Cox point processes model with low- to fine-grained discretizations.<\/jats:p>","DOI":"10.1093\/biomet\/asy074","type":"journal-article","created":{"date-parts":[[2018,12,12]],"date-time":"2018-12-12T15:11:37Z","timestamp":1544627497000},"page":"287-302","source":"Crossref","is-referenced-by-count":38,"title":["Unbiased Hamiltonian Monte Carlo with couplings"],"prefix":"10.1093","volume":"106","author":[{"given":"J","family":"Heng","sequence":"first","affiliation":[{"name":"ESSEC Business School, 5 Nepal Park, Singapore 139408, Republic of Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"P E","family":"Jacob","sequence":"first","affiliation":[{"name":"Department of Statistics, Harvard University, 1 Oxford Street, Cambridge, Massachusetts 02138, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2019,2,28]]},"reference":[{"key":"2020030521300842400_B1","doi-asserted-by":"crossref","first-page":"1501","DOI":"10.3150\/12-BEJ414","article-title":"Optimal tuning of the hybrid Monte Carlo algorithm","volume":"19","author":"Beskos,","year":"2013","journal-title":"Bernoulli"},{"key":"2020030521300842400_B2","article-title":"A conceptual introduction to Hamiltonian Monte Carlo","author":"Betancourt,","year":"2017"},{"key":"2020030521300842400_B3","doi-asserted-by":"crossref","first-page":"2257","DOI":"10.3150\/16-BEJ810","article-title":"The geometric foundations of Hamiltonian Monte Carlo","volume":"23","author":"Betancourt,","year":"2017","journal-title":"Bernoulli"},{"key":"2020030521300842400_B4","article-title":"Coupling and convergence for Hamiltonian Monte Carlo","author":"Bou-Rabee,","year":"2018"},{"key":"2020030521300842400_B5","doi-asserted-by":"crossref","first-page":"113","DOI":"10.1017\/S0962492917000101","article-title":"Geometric integrators and the Hamiltonian Monte Carlo method","volume":"27","author":"Bou-Rabee,","year":"2018","journal-title":"Acta Numer."},{"key":"2020030521300842400_B6","doi-asserted-by":"crossref","DOI":"10.1201\/b10905","volume-title":"Handbook of Markov Chain Monte Carlo","author":"Brooks,","year":"2011"},{"key":"2020030521300842400_B7","doi-asserted-by":"crossref","first-page":"17408","DOI":"10.1073\/pnas.1408184111","article-title":"A general construction for parallelizing Metropolis\u2013Hastings algorithms","volume":"111","author":"Calderhead,","year":"2014","journal-title":"Proc. Nat. Acad. Sci."},{"key":"2020030521300842400_B8","doi-asserted-by":"crossref","first-page":"351","DOI":"10.1051\/m2an:2007014","article-title":"Theoretical and numerical comparison of some sampling methods for molecular dynamics","volume":"41","author":"Cances,","year":"2007","journal-title":"ESAIM Math. Mod. Numer. Anal."},{"key":"2020030521300842400_B9","first-page":"1","article-title":"Stan: A probabilistic programming language","volume":"20","author":"Carpenter,","year":"2016","journal-title":"J. Statist. Software"},{"key":"2020030521300842400_B10","doi-asserted-by":"crossref","first-page":"299","DOI":"10.1198\/000313001753272240","article-title":"Explaining the perfect sampler","volume":"55","author":"Casella,","year":"2001","journal-title":"Am. Statistician"},{"key":"2020030521300842400_B11","doi-asserted-by":"crossref","first-page":"253","DOI":"10.1111\/j.1467-9868.2005.00500.x","article-title":"Scaling limits for the transient phase of local Metropolis\u2013Hastings algorithms","volume":"67","author":"Christensen,","year":"2005","journal-title":"J. R. Statist. Soc. B"},{"key":"2020030521300842400_B12","doi-asserted-by":"crossref","first-page":"280","DOI":"10.1111\/j.0006-341X.2002.00280.x","article-title":"Bayesian prediction of spatial count data using generalized linear mixed models","volume":"58","author":"Christensen,","year":"2002","journal-title":"Biometrics"},{"key":"2020030521300842400_B13","doi-asserted-by":"crossref","first-page":"216","DOI":"10.1016\/0370-2693(87)91197-X","article-title":"Hybrid Monte Carlo","volume":"195","author":"Duane,","year":"1987","journal-title":"Phys. Lett. B"},{"key":"2020030521300842400_B14","article-title":"On the convergence of Hamiltonian Monte Carlo","author":"Durmus,","year":"2017"},{"key":"2020030521300842400_B15","doi-asserted-by":"crossref","first-page":"386","DOI":"10.1214\/18-STS648","article-title":"Piecewise deterministic Markov processes for continuous-time Monte Carlo","volume":"33","author":"Fearnhead,","year":"2018","journal-title":"Statist. Sci."},{"key":"2020030521300842400_B16","doi-asserted-by":"crossref","first-page":"123","DOI":"10.1111\/j.1467-9868.2010.00765.x","article-title":"Riemann manifold Langevin and Hamiltonian Monte Carlo methods","volume":"73","author":"Girolami,","year":"2011","journal-title":"J. R. Statist. Soc. B"},{"key":"2020030521300842400_B17","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1145\/102810.102811","article-title":"Analysis of parallel replicated simulations under a completion time constraint","volume":"1","author":"Glynn,","year":"1991","journal-title":"ACM Trans. Mod. Comp. Simul."},{"key":"2020030521300842400_B18","doi-asserted-by":"crossref","first-page":"377","DOI":"10.1239\/jap\/1417528487","article-title":"Exact estimation for Markov chain equilibrium expectations","volume":"51","author":"Glynn,","year":"2014","journal-title":"J. Appl. Prob."},{"key":"2020030521300842400_B19","doi-asserted-by":"crossref","first-page":"505","DOI":"10.1287\/opre.40.3.505","article-title":"The asymptotic efficiency of simulation estimators","volume":"40","author":"Glynn,","year":"1992","journal-title":"Oper. Res."},{"key":"2020030521300842400_B20","volume-title":"Geometric Numerical Integration: Structure-Preserving Algorithms for Ordinary Differential Equations","author":"Hairer,","year":"2005"},{"key":"2020030521300842400_B21","first-page":"1593","article-title":"The No-U-Turn Sampler: Adaptively setting path lengths in Hamiltonian Monte Carlo","volume":"15","author":"Hoffman,","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"2020030521300842400_B22","doi-asserted-by":"crossref","first-page":"247","DOI":"10.1016\/0370-2693(91)90812-5","article-title":"A generalized guided Monte Carlo algorithm","volume":"268","author":"Horowitz,","year":"1991","journal-title":"Phys. Lett. B"},{"key":"2020030521300842400_B23","volume-title":"Perfect Simulation, vol. 148 of Monographs on Statistics & Applied Probability","author":"Huber,","year":"2016"},{"key":"2020030521300842400_B24","article-title":"Smoothing with couplings of conditional particle filters","author":"Jacob,","year":"2017"},{"key":"2020030521300842400_B25","article-title":"Unbiased Markov chain Monte Carlo with couplings","author":"Jacob,","year":"2019"},{"key":"2020030521300842400_B26","doi-asserted-by":"crossref","first-page":"238","DOI":"10.1080\/01621459.1998.10474105","article-title":"A coupling-regeneration scheme for diagnosing convergence in Markov chain Monte Carlo algorithms","volume":"93","author":"Johnson,","year":"1998","journal-title":"J. Am. Statist. Assoc."},{"key":"2020030521300842400_B27","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1007\/s11009-011-9237-8","article-title":"CLTs and asymptotic variance of time-sampled Markov chains","volume":"15","author":"\u0141atuszy\u0144ski,","year":"2013","journal-title":"Methodol. Comp. Appl. Prob."},{"key":"2020030521300842400_B28","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-16375-8","volume-title":"Molecular Dynamics.","author":"Leimkuhler,","year":"2015"},{"key":"2020030521300842400_B29","doi-asserted-by":"crossref","DOI":"10.1142\/p579","volume-title":"Free Energy Computations: A Mathematical Perspective","author":"Leli\u00e8vre,","year":"2010"},{"key":"2020030521300842400_B30","article-title":"On the geometric ergodicity of Hamiltonian Monte Carlo","author":"Livingstone,","year":"2016"},{"key":"2020030521300842400_B31","doi-asserted-by":"crossref","first-page":"303","DOI":"10.1093\/biomet\/asz013","article-title":"Kinetic energy choice in Hamiltonian\/hybrid Monte Carlo","volume":"106","author":"Livingstone,","year":"2019","journal-title":"Biometrika"},{"key":"2020030521300842400_B32","article-title":"Rapid mixing of Hamiltonian Monte Carlo on strongly log-concave distributions","author":"Mangoubi,","year":"2017"},{"key":"2020030521300842400_B33","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9780511626630","volume-title":"Markov Chains and Stochastic Stability","author":"Meyn,","year":"2009","edition":"2nd ed"},{"key":"2020030521300842400_B34","doi-asserted-by":"crossref","first-page":"451","DOI":"10.1111\/1467-9469.00115","article-title":"Log Gaussian Cox processes","volume":"25","author":"M\u00f8ller,","year":"1998","journal-title":"Scand. J. Statist."},{"key":"2020030521300842400_B35","doi-asserted-by":"crossref","first-page":"233","DOI":"10.1080\/01621459.1995.10476507","article-title":"Regeneration in Markov chain samplers","volume":"90","author":"Mykland,","year":"1995","journal-title":"J. Am. Statist. Assoc."},{"key":"2020030521300842400_B36","first-page":"475","volume-title":"Advances in Neural Information Processing Systems 5 (NIPS 1992)","author":"Neal,","year":"1993"},{"key":"2020030521300842400_B37","article-title":"Circularly-coupled Markov chain sampling","author":"Neal,","year":"2017"},{"key":"2020030521300842400_B38","doi-asserted-by":"crossref","first-page":"607","DOI":"10.1093\/biomet\/60.3.607","article-title":"Optimum Monte-Carlo sampling using Markov chains","volume":"60","author":"Peskun,","year":"1973","journal-title":"Biometrika"},{"key":"2020030521300842400_B39","first-page":"7","article-title":"CODA: Convergence diagnosis and output analysis for MCMC","volume":"6","author":"Plummer,","year":"2006","journal-title":"R News"},{"issue":"chap. 3","key":"2020030521300842400_B40","article-title":"Total variation distance between measures","author":"Pollard,","year":"2005","journal-title":"Asymptopia"},{"key":"2020030521300842400_B41","article-title":"The scalable Langevin exact algorithm: Bayesian inference for big data","author":"Pollock,","year":"2017"},{"key":"2020030521300842400_B42","volume-title":"R: A Language and Environment for Statistical Computing","year":"2019"},{"key":"2020030521300842400_B43","doi-asserted-by":"crossref","first-page":"110","DOI":"10.1214\/aoap\/1034625254","article-title":"Weak convergence and optimal scaling of random walk Metropolis algorithms","volume":"7","author":"Roberts,","year":"1997","journal-title":"Ann. Appl. Prob."},{"key":"2020030521300842400_B44","doi-asserted-by":"crossref","first-page":"255","DOI":"10.1111\/1467-9868.00123","article-title":"Optimal scaling of discrete approximations to Langevin diffusions","volume":"60","author":"Roberts,","year":"1998","journal-title":"J. R. Statist. Soc. B"},{"key":"2020030521300842400_B45","doi-asserted-by":"crossref","first-page":"372","DOI":"10.1006\/aama.1996.0515","article-title":"Faithful couplings of Markov chains: now equals forever","volume":"18","author":"Rosenthal,","year":"1997","journal-title":"Adv. Appl. Math."},{"key":"2020030521300842400_B46","first-page":"207","article-title":"Parallel computing and Monte Carlo algorithms","volume":"4","author":"Rosenthal,","year":"2000","journal-title":"Far East J. Theor. Statist."},{"key":"2020030521300842400_B47","article-title":"Piecewise deterministic Markov chain Monte Carlo","author":"Vanetti,","year":"2018"}],"container-title":["Biometrika"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/academic.oup.com\/biomet\/article-pdf\/106\/2\/287\/28575474\/asy074.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"http:\/\/academic.oup.com\/biomet\/article-pdf\/106\/2\/287\/28575474\/asy074.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,11]],"date-time":"2023-09-11T22:49:15Z","timestamp":1694472555000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/biomet\/article\/106\/2\/287\/5366709"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,2,28]]},"references-count":47,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2019,2,28]]},"published-print":{"date-parts":[[2019,6,1]]}},"URL":"https:\/\/doi.org\/10.1093\/biomet\/asy074","relation":{},"ISSN":["0006-3444","1464-3510"],"issn-type":[{"value":"0006-3444","type":"print"},{"value":"1464-3510","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2019,6]]},"published":{"date-parts":[[2019,2,28]]}}}