{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T19:22:34Z","timestamp":1791919354723,"version":"4.3.4"},"reference-count":37,"publisher":"Oxford University Press (OUP)","issue":"3","license":[{"start":{"date-parts":[[2016,4,23]],"date-time":"2016-04-23T00:00:00Z","timestamp":1461369600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/journals\/pages\/open_access\/funder_policies\/chorus\/standard_publication_model"}],"funder":[{"name":"Investissements d'Avenir","award":["ANR-11-IDEX-0003\/Labex Ecodec\/ANR-11-LABX-0047"],"award-info":[{"award-number":["ANR-11-IDEX-0003\/Labex Ecodec\/ANR-11-LABX-0047"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017,6,1]]},"abstract":"<jats:title>Summary<\/jats:title>\n                  <jats:p>Sampling from various kinds of distribution is an issue of paramount importance in statistics since it is often the key ingredient for constructing estimators, test procedures or confidence intervals. In many situations, exact sampling from a given distribution is impossible or computationally expensive and, therefore, one needs to resort to approximate sampling strategies. However, there is no well-developed theory providing meaningful non-asymptotic guarantees for the approximate sampling procedures, especially in high dimensional problems. The paper makes some progress in this direction by considering the problem of sampling from a distribution having a smooth and log-concave density defined on Rp, for some integer p &amp;gt; 0. We establish non-asymptotic bounds for the error of approximating the target distribution by the distribution obtained by the Langevin Monte Carlo method and its variants. We illustrate the effectiveness of the established guarantees with various experiments. Underlying our analysis are insights from the theory of continuous time diffusion processes, which may be of interest beyond the framework of log-concave densities that are considered in the present work.<\/jats:p>","DOI":"10.1111\/rssb.12183","type":"journal-article","created":{"date-parts":[[2016,4,23]],"date-time":"2016-04-23T08:07:49Z","timestamp":1461398869000},"page":"651-676","source":"Crossref","is-referenced-by-count":216,"title":["Theoretical Guarantees for Approximate Sampling from Smooth and Log-Concave Densities"],"prefix":"10.1093","volume":"79","author":[{"given":"Arnak S.","family":"Dalalyan","sequence":"first","affiliation":[{"name":"ParisTech , Paris , France"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2016,4,23]]},"reference":[{"key":"2023021709322576700_rssb12183-cit-0001","doi-asserted-by":"crossref","first-page":"32","DOI":"10.1017\/CBO9780511984679.003","article-title":"Adaptive Markov chain Monte Carlo: theory and methods","author":"Atchad\u00e9","year":"2011","journal-title":"Bayesian Time Series Models"},{"key":"2023021709322576700_rssb12183-cit-0002","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-00227-9","volume-title":"Analysis and Geometry of Markov Diffusion Operators","author":"Bakry","year":"2014"},{"key":"2023021709322576700_rssb12183-cit-0003","doi-asserted-by":"crossref","first-page":"2011","DOI":"10.1214\/08-AOS634","article-title":"On the computational complexity of MCMC-based estimators in large samples","volume":"37","author":"Belloni","year":"2009","journal-title":"Ann. Statist."},{"key":"2023021709322576700_rssb12183-cit-0004","doi-asserted-by":"crossref","first-page":"80","DOI":"10.1093\/imanum\/drs003","article-title":"Nonasymptotic mixing of the MALA algorithm. IMA J","volume":"33","author":"Bou-Rabee","year":"2013","journal-title":"Numer. Anal."},{"key":"2023021709322576700_rssb12183-cit-0005","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9780511804441","author":"Boyd","year":"2004","journal-title":"Convex Optimization"},{"key":"2023021709322576700_rssb12183-cit-0006","doi-asserted-by":"crossref","first-page":"398","DOI":"10.1214\/aos\/1030563991","article-title":"MCMC convergence diagnosis via multivariate bounds on log-concave densities","volume":"26","author":"Brooks","year":"1998","journal-title":"Ann. Statist."},{"key":"2023021709322576700_rssb12183-cit-0007","doi-asserted-by":"crossref","first-page":"1239","DOI":"10.1090\/S0002-9947-97-01812-6","article-title":"Estimation of spectral gap for elliptic operators","volume":"349","author":"Chen","year":"1997","journal-title":"Trans. Am. Math. Soc."},{"key":"2023021709322576700_rssb12183-cit-0008","first-page":"1","volume-title":"Sparse regression learning by aggregation and Langevin Monte-Carlo","author":"Dalalyan","year":"2009"},{"key":"2023021709322576700_rssb12183-cit-0009","doi-asserted-by":"crossref","first-page":"1423","DOI":"10.1016\/j.jcss.2011.12.023","article-title":"Sparse regression learning by aggregation and Langevin Monte-Carlo","volume":"78","author":"Dalalyan","year":"2012","journal-title":"J. Comput. Syst. Sci."},{"key":"2023021709322576700_rssb12183-cit-0010","doi-asserted-by":"crossref","first-page":"1643","DOI":"10.1214\/105051604000000620","article-title":"Quantitative bounds on convergence of time-inhomogeneous Markov chains","volume":"14","author":"Douc","year":"2004","journal-title":"Ann. Appl. Probab."},{"key":"2023021709322576700_rssb12183-cit-0011","volume-title":"Non-asymptotic convergence analysis for the unadjusted langevin algorithm","author":"Durmus","year":"2015"},{"key":"2023021709322576700_rssb12183-cit-0012","doi-asserted-by":"crossref","first-page":"14","DOI":"10.1214\/aoap\/1029962595","article-title":"Log-Sobolev inequalities and sampling from log-concave distributions","volume":"9","author":"Frieze","year":"1999","journal-title":"Ann. Appl. Probab."},{"key":"2023021709322576700_rssb12183-cit-0013","first-page":"812","article-title":"Sampling from log-concave distributions","volume":"4","author":"Frieze","year":"1994","journal-title":"Ann. Appl. Probab."},{"key":"2023021709322576700_rssb12183-cit-0014","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 (with discussion)","volume":"73","author":"Girolami","year":"2011","journal-title":"J. R. Statist. Soc."},{"key":"2023021709322576700_rssb12183-cit-0015","first-page":"597","article-title":"Informative g-priors for logistic regression","volume":"9","author":"Hanson","year":"2014","journal-title":"Baysn Anal."},{"key":"2023021709322576700_rssb12183-cit-0016","first-page":"145","article-title":"Bayesian auxiliary variable models for binary and multinomial regression","volume":"1","author":"Holmes","year":"2006","journal-title":"Baysn Anal."},{"key":"2023021709322576700_rssb12183-cit-0017","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":"Stoch. Processes Appl."},{"key":"2023021709322576700_rssb12183-cit-0018","first-page":"367","article-title":"Recursive computation of the invariant distribution of a diffusion","volume":"8","author":"Lamberton","year":"2002","journal-title":"Bernoulli"},{"key":"2023021709322576700_rssb12183-cit-0019","volume-title":"Estimation num\u00e9rique de la mesure invariante d'un processus de diffusion","author":"Lemaire","year":"2005"},{"key":"2023021709322576700_rssb12183-cit-0020","doi-asserted-by":"crossref","first-page":"985","DOI":"10.1137\/S009753970544727X","article-title":"Hit-and-run from a corner","volume":"35","author":"Lov\u00e1sz","year":"2006","journal-title":"SIAM J. Comput."},{"key":"2023021709322576700_rssb12183-cit-0021","first-page":"57","volume-title":"Fast algorithms for logconcave functions: sampling, rounding, integration and optimization","author":"Lov\u00e1sz","year":"2006"},{"key":"2023021709322576700_rssb12183-cit-0022","doi-asserted-by":"crossref","first-page":"981","DOI":"10.1214\/aoap\/1177004900","article-title":"Computable bounds for geometric convergence rates of Markov chains","volume":"4","author":"Meyn","year":"1994","journal-title":"Ann. Appl. Probab."},{"key":"2023021709322576700_rssb12183-cit-0023","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4419-8853-9","volume-title":"Introductory Lectures on Convex Optimization","author":"Nesterov","year":"2004"},{"key":"2023021709322576700_rssb12183-cit-0024","first-page":"113","article-title":"A bridge between nonlinear time series models and nonlinear stochastic dynamical systems: a local linearization approach","volume":"2","author":"Ozaki","year":"1992","journal-title":"Statist. Sin."},{"key":"2023021709322576700_rssb12183-cit-0025","volume-title":"Proximal markov chain monte carlo algorithms","author":"Pereyra","year":"2014"},{"key":"2023021709322576700_rssb12183-cit-0026","doi-asserted-by":"crossref","first-page":"2320","DOI":"10.1214\/11-AAP828","article-title":"Optimal scaling and diffusion limits for the Langevin algorithm in high dimensions","volume":"22","author":"Pillai","year":"2012","journal-title":"Ann. Appl. Probab."},{"key":"2023021709322576700_rssb12183-cit-0027","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."},{"key":"2023021709322576700_rssb12183-cit-0028","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":"Probab. Surv."},{"key":"2023021709322576700_rssb12183-cit-0029","doi-asserted-by":"crossref","first-page":"337","DOI":"10.1023\/A:1023562417138","article-title":"Langevin diffusions and Metropolis-Hastings algorithms","volume":"4","author":"Roberts","year":"2002","journal-title":"Methodol. Comput. Appl. Probab."},{"key":"2023021709322576700_rssb12183-cit-0030","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":"2023021709322576700_rssb12183-cit-0031","first-page":"123","article-title":"Quantitative convergence rates of Markov chains: a simple account","volume":"7","author":"Rosenthal","year":"2002","journal-title":"Electron. Communs Probab."},{"key":"2023021709322576700_rssb12183-cit-0032","doi-asserted-by":"crossref","first-page":"2463","DOI":"10.1214\/12-EJS756","article-title":"Convergence rates for MCMC algorithms for a robust Bayesian binary regression model","volume":"6","author":"Roy","year":"2012","journal-title":"Electron. J. Statist"},{"key":"2023021709322576700_rssb12183-cit-0033","doi-asserted-by":"crossref","first-page":"45","DOI":"10.1214\/14-SS107","article-title":"Log-concavity and strong log-concavity: a review","volume":"8","author":"Saumard","year":"2014","journal-title":"Statist. Surv."},{"key":"2023021709322576700_rssb12183-cit-0034","volume-title":"A shrinkage-thresholding metropolis adjusted langevin algorithm for bayesian variable selection","author":"Schreck","year":"2013"},{"key":"2023021709322576700_rssb12183-cit-0035","doi-asserted-by":"crossref","first-page":"283","DOI":"10.1023\/A:1010086427957","article-title":"Langevin-type models: I, Diffusions with given stationary distributions and their discretizations","volume":"1","author":"Stramer","year":"1999","journal-title":"Methodol. Comput. Appl. Probab."},{"key":"2023021709322576700_rssb12183-cit-0036","doi-asserted-by":"crossref","first-page":"307","DOI":"10.1023\/A:1010090512027","article-title":"Langevin-type models: II, Self-targeting candidates for MCMC algorithms","volume":"1","author":"Stramer","year":"1999","journal-title":"Methodol. Comput. Appl. Probab."},{"key":"2023021709322576700_rssb12183-cit-0037","doi-asserted-by":"crossref","first-page":"14","DOI":"10.1016\/j.spl.2014.04.002","article-title":"Langevin diffusions and the Metropolis-adjusted Langevin algorithm","volume":"91","author":"Xifara","year":"2014","journal-title":"Statist. Probab. Lett."}],"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.12183","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.wiley.com\/onlinelibrary\/tdm\/v1\/articles\/10.1111%2Frssb.12183","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/academic.oup.com\/jrsssb\/article-pdf\/79\/3\/651\/49214807\/jrsssb_79_3_651.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jrsssb\/article-pdf\/79\/3\/651\/49214807\/jrsssb_79_3_651.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,17]],"date-time":"2023-02-17T04:53:13Z","timestamp":1676609593000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jrsssb\/article\/79\/3\/651\/7040689"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,4,23]]},"references-count":37,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2016,4,23]]},"published-print":{"date-parts":[[2017,6,1]]}},"URL":"https:\/\/doi.org\/10.1111\/rssb.12183","relation":{},"ISSN":["1369-7412","1467-9868"],"issn-type":[{"value":"1369-7412","type":"print"},{"value":"1467-9868","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2017,6]]},"published":{"date-parts":[[2016,4,23]]}}}