{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,15]],"date-time":"2026-10-15T06:58:10Z","timestamp":1792047490313,"version":"4.4.0"},"reference-count":39,"publisher":"Oxford University Press (OUP)","issue":"2","license":[{"start":{"date-parts":[[2023,2,24]],"date-time":"2023-02-24T00:00:00Z","timestamp":1677196800000},"content-version":"vor","delay-in-days":409,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100000266","name":"Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","award":["EP\/K014463\/1"],"award-info":[{"award-number":["EP\/K014463\/1"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100010663","name":"European Research Council","doi-asserted-by":"publisher","award":["306406 (N-BNP)"],"award-info":[{"award-number":["306406 (N-BNP)"]}],"id":[{"id":"10.13039\/100010663","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,4,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>There is a tension between robustness and efficiency when designing Markov chain Monte Carlo (MCMC) sampling algorithms. Here we focus on robustness with respect to tuning parameters, showing that more sophisticated algorithms tend to be more sensitive to the choice of step-size parameter and less robust to heterogeneity of the distribution of interest. We characterise this phenomenon by studying the behaviour of spectral gaps as an increasingly poor step-size is chosen for the algorithm. Motivated by these considerations, we propose a novel and simple gradient-based MCMC algorithm, inspired by the classical Barker accept-reject rule, with improved robustness properties. Extensive theoretical results, dealing with robustness to tuning, geometric ergodicity and scaling with dimension, suggest that the novel scheme combines the robustness of simple schemes with the efficiency of gradient-based ones. We show numerically that this type of robustness is particularly beneficial in the context of adaptive MCMC, giving examples where our proposed scheme significantly outperforms state-of-the-art alternatives.<\/jats:p>","DOI":"10.1111\/rssb.12482","type":"journal-article","created":{"date-parts":[[2022,1,11]],"date-time":"2022-01-11T07:33:10Z","timestamp":1641886390000},"page":"496-523","source":"Crossref","is-referenced-by-count":36,"title":["The Barker Proposal: Combining Robustness and Efficiency in Gradient-Based MCMC"],"prefix":"10.1093","volume":"84","author":[{"given":"Samuel","family":"Livingstone","sequence":"first","affiliation":[{"name":"Department of Statistical Science , , UK"},{"name":"University College London , , UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Giacomo","family":"Zanella","sequence":"additional","affiliation":[{"name":"Department of Decision Sciences , , Milan , Italy"},{"name":"BIDSA and IGIER, Bocconi University , , Milan , Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2022,1,11]]},"reference":[{"key":"2023022408360090400_","doi-asserted-by":"crossref","first-page":"343","DOI":"10.1007\/s11222-008-9110-y","article-title":"A tutorial on adaptive MCMC","volume":"18","author":"Andrieu","year":"2008","journal-title":"Statistics and Computing"},{"key":"2023022408360090400_","doi-asserted-by":"crossref","first-page":"235","DOI":"10.1007\/s11009-006-8550-0","article-title":"An adaptive version for the Metropolis adjusted Langevin algorithm with a truncated drift","volume":"8","author":"Atchade","year":"2006","journal-title":"Methodology and Computing in Applied Probability"},{"key":"2023022408360090400_","first-page":"171","article-title":"A class of distributions which includes the normal ones","volume":"12","author":"Azzalini","year":"1985","journal-title":"Scandinavian Journal of Statistics"},{"key":"2023022408360090400_","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9781139248891","volume-title":"The skew-normal and related families","author":"Azzalini","year":"2013"},{"key":"2023022408360090400_","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1071\/PH650119","article-title":"Monte Carlo calculations of the radial distribution functions for a proton-electron plasma","volume":"18","author":"Barker","year":"1965","journal-title":"Australian Journal of Physics"},{"key":"2023022408360090400_","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":"2023022408360090400_","doi-asserted-by":"crossref","first-page":"2966","DOI":"10.1214\/18-AAP1380","article-title":"Asymptotic analysis of the random walk metropolis algorithm on ridged densities","volume":"28","author":"Beskos","year":"2018","journal-title":"The Annals of Applied Probability"},{"key":"2023022408360090400_","doi-asserted-by":"crossref","DOI":"10.1201\/b10905","volume-title":"Handbook of Markov chain Monte Carlo","author":"Brooks","year":"2011"},{"issue":"10","key":"2023022408360090400_","doi-asserted-by":"crossref","first-page":"3638","DOI":"10.1016\/j.spa.2018.10.002","article-title":"The tamed unadjusted Langevin algorithm","volume":"129","author":"Brosse","year":"2018","journal-title":"Stochastic Processes and their Applications"},{"key":"2023022408360090400_","doi-asserted-by":"crossref","first-page":"651","DOI":"10.1111\/rssb.12183","article-title":"Theoretical guarantees for approximate sampling from smooth and log-concave densities","volume":"79","author":"Dalalyan","year":"2017","journal-title":"Journal of the Royal Statistical Society: Series B (Statistical Methodology)"},{"key":"2023022408360090400_","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":"Physics Letters B"},{"key":"2023022408360090400_","doi-asserted-by":"crossref","first-page":"1551","DOI":"10.1214\/16-AAP1238","article-title":"Nonasymptotic convergence analysis for the unadjusted Langevin algorithm","volume":"27","author":"Durmus","year":"2017","journal-title":"The Annals of Applied Probability"},{"key":"2023022408360090400_","volume-title":"On the convergence of Hamiltonian Monte Carlo","author":"Durmus","year":"2017"},{"key":"2023022408360090400_","doi-asserted-by":"crossref","first-page":"2195","DOI":"10.1214\/16-AAP1257","article-title":"Fast Langevin based algorithm for MCMC in high dimensions","volume":"27","author":"Durmus","year":"2017","journal-title":"The Annals of Applied Probability"},{"issue":"1","key":"2023022408360090400_","doi-asserted-by":"crossref","first-page":"97","DOI":"10.1093\/biomet\/57.1.97","article-title":"Monte Carlo sampling methods using Markov chains and their applications","volume":"57","author":"Hastings","year":"1970","journal-title":"Biometrika"},{"key":"2023022408360090400_","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":"Journal of Machine Learning Research"},{"key":"2023022408360090400_","doi-asserted-by":"crossref","first-page":"341","DOI":"10.1016\/S0304-4149(99)00082-4","article-title":"Geometric ergodicity of Metropolis algorithms","volume":"85","author":"Jarner","year":"2000","journal-title":"Stochastic Processes and their Applications"},{"key":"2023022408360090400_","doi-asserted-by":"crossref","DOI":"10.1093\/oso\/9780198515357.001.0001","volume-title":"Statistical mechanics: algorithms and computations","author":"Krauth","year":"2006"},{"key":"2023022408360090400_","doi-asserted-by":"crossref","first-page":"3109","DOI":"10.3150\/18-BEJ1083","article-title":"On the geometric ergodicity of Hamiltonian Monte Carlo","volume":"25","author":"Livingstone","year":"2019","journal-title":"Bernoulli"},{"key":"2023022408360090400_","doi-asserted-by":"crossref","first-page":"881","DOI":"10.1214\/10-AAP754","article-title":"Diffusion limits of the random walk Metropolis algorithm in high dimensions","volume":"22","author":"Mattingly","year":"2012","journal-title":"The Annals of Applied Probability"},{"key":"2023022408360090400_","doi-asserted-by":"crossref","first-page":"1087","DOI":"10.1063\/1.1699114","article-title":"Equation of state calculations by fast computing machines","volume":"21","author":"Metropolis","year":"1953","journal-title":"The Journal of Chemical Physics"},{"key":"2023022408360090400_","doi-asserted-by":"crossref","first-page":"705","DOI":"10.1214\/aos\/1056562461","article-title":"Slice sampling","volume":"31","author":"Neal","year":"2003","journal-title":"The Annals of Statistics"},{"key":"2023022408360090400_","first-page":"2","article-title":"MCMC using Hamiltonian dynamics","volume":"2","author":"Neal","year":"2011","journal-title":"Handbook of Markov Chain Monte Carlo"},{"key":"2023022408360090400_","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":"2023022408360090400_","first-page":"7","article-title":"Coda: convergence diagnosis and output analysis for MCMC","volume":"6","author":"Plummer","year":"2006","journal-title":"R News"},{"key":"2023022408360090400_","volume-title":"Accelerated sampling on discrete spaces with non-reversible Markov processes","author":"Power","year":"2019"},{"key":"2023022408360090400_","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":"Journal of the Royal Statistical Society: Series B (Statistical Methodology)"},{"key":"2023022408360090400_","doi-asserted-by":"crossref","first-page":"351","DOI":"10.1214\/ss\/1015346320","article-title":"Optimal scaling for various Metropolis-Hastings algorithms","volume":"16","author":"Roberts","year":"2001","journal-title":"Statistical Science"},{"key":"2023022408360090400_","doi-asserted-by":"crossref","first-page":"20","DOI":"10.1214\/154957804100000024","article-title":"General state space Markov chains and MCMC algorithms","volume":"1","author":"Roberts","year":"2004","journal-title":"Probability Surveys"},{"key":"2023022408360090400_","doi-asserted-by":"crossref","first-page":"410","DOI":"10.1017\/jpr.2016.9","article-title":"Complexity bounds for Markov chain Monte Carlo algorithms via diffusion limits","volume":"53","author":"Roberts","year":"2016","journal-title":"Journal of Applied Probability"},{"key":"2023022408360090400_","doi-asserted-by":"crossref","first-page":"341","DOI":"10.2307\/3318418","article-title":"Exponential convergence of Langevin distributions and their discrete approximations","volume":"2","author":"Roberts","year":"1996","journal-title":"Bernoulli"},{"key":"2023022408360090400_","first-page":"110","article-title":"Weak convergence and optimal scaling of random walk Metropolis algorithms","volume":"7","author":"Roberts","year":"1997","journal-title":"The Annals of Applied Probability"},{"key":"2023022408360090400_","doi-asserted-by":"crossref","first-page":"169","DOI":"10.1198\/016214503388619193","article-title":"Asymptotic variance and convergence rates of nearly-periodic Markov chain Monte Carlo algorithms","volume":"98","author":"Rosenthal","year":"2003","journal-title":"Journal of the American Statistical Association"},{"key":"2023022408360090400_","volume-title":"Exploring an adaptive Metropolis algorithm","author":"Shaby","year":"2010"},{"key":"2023022408360090400_","volume-title":"RStan: the R interface to Stan","author":"Stan Development Team","year":"2020"},{"key":"2023022408360090400_","doi-asserted-by":"crossref","first-page":"451","DOI":"10.1017\/S0962492910000061","article-title":"Inverse problems: a Bayesian perspective","volume":"19","author":"Stuart","year":"2010","journal-title":"Acta Numerica"},{"key":"2023022408360090400_","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1214\/aoap\/1027961031","article-title":"A note on Metropolis-Hastings kernels for general state spaces","volume":"8","author":"Tierney","year":"1998","journal-title":"The Annals of Applied Probability"},{"key":"2023022408360090400_","doi-asserted-by":"crossref","first-page":"780","DOI":"10.1214\/EJP.v14-638","article-title":"Sufficient conditions for torpid mixing of parallel and simulated tempering","volume":"14","author":"Woodard","year":"2009","journal-title":"Electronic Journal of Probability"},{"key":"2023022408360090400_","doi-asserted-by":"crossref","first-page":"852","DOI":"10.1080\/01621459.2019.1585255","article-title":"Informed proposals for local MCMC in discrete spaces","volume":"115","author":"Zanella","year":"2020","journal-title":"Journal of the American Statistical Association"}],"container-title":["Journal of the Royal Statistical Society Series B: Statistical Methodology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/rssb.12482","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1111\/rssb.12482","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/academic.oup.com\/jrsssb\/article-pdf\/84\/2\/496\/49322274\/jrsssb_84_2_496.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jrsssb\/article-pdf\/84\/2\/496\/49322274\/jrsssb_84_2_496.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,15]],"date-time":"2023-11-15T12:28:03Z","timestamp":1700051283000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jrsssb\/article\/84\/2\/496\/7056132"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,1,11]]},"references-count":39,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2022,1,11]]},"published-print":{"date-parts":[[2022,4,1]]}},"URL":"https:\/\/doi.org\/10.1111\/rssb.12482","relation":{},"ISSN":["1369-7412","1467-9868"],"issn-type":[{"value":"1369-7412","type":"print"},{"value":"1467-9868","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2022,4]]},"published":{"date-parts":[[2022,1,11]]}}}