{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,3]],"date-time":"2026-08-03T13:39:20Z","timestamp":1785764360770,"version":"3.56.0"},"reference-count":68,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2021,3,19]],"date-time":"2021-03-19T00:00:00Z","timestamp":1616112000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2021,3,19]],"date-time":"2021-03-19T00:00:00Z","timestamp":1616112000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Stat Comput"],"published-print":{"date-parts":[[2021,5]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Stochastic approximation methods play a central role in maximum likelihood estimation problems involving intractable likelihood functions, such as marginal likelihoods arising in problems with missing or incomplete data, and in parametric empirical Bayesian estimation. Combined with Markov chain Monte Carlo algorithms, these stochastic optimisation methods have been successfully applied to a wide range of problems in science and industry. However, this strategy scales poorly to large problems because of methodological and theoretical difficulties related to using high-dimensional Markov chain Monte Carlo algorithms within a stochastic approximation scheme. This paper proposes to address these difficulties by using unadjusted Langevin algorithms to construct the stochastic approximation. This leads to a highly efficient stochastic optimisation methodology with favourable convergence properties that can be quantified explicitly and easily checked. The proposed methodology is demonstrated with three experiments, including a challenging application to statistical audio analysis and a sparse Bayesian logistic regression with random effects problem.<\/jats:p>","DOI":"10.1007\/s11222-020-09986-y","type":"journal-article","created":{"date-parts":[[2021,3,19]],"date-time":"2021-03-19T13:04:49Z","timestamp":1616159089000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":17,"title":["Efficient stochastic optimisation by unadjusted Langevin Monte Carlo"],"prefix":"10.1007","volume":"31","author":[{"given":"Valentin","family":"De Bortoli","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alain","family":"Durmus","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marcelo","family":"Pereyra","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ana F.","family":"Vidal","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2021,3,19]]},"reference":[{"key":"9986_CR1","unstructured":"Ahn, S., Korattikara, A., Welling, M.: Bayesian posterior sampling via stochastic gradient fisher scoring. (2012) arXiv preprint arXiv:1206.6380,"},{"key":"9986_CR2","unstructured":"Ahn, S., Shahbaba, B., Welling, M.: Distributed stochastic gradient mcmc. In: International Conference on Machine Learning, pp. 1044\u20131052, (2014)"},{"issue":"3","key":"9986_CR3","doi-asserted-by":"publisher","first-page":"1462","DOI":"10.1214\/105051606000000286","volume":"16","author":"C Andrieu","year":"2006","unstructured":"Andrieu, C., Moulines, E.: On the ergodicity properties of some adaptive MCMC algorithms. Ann. Appl. Probab. 16(3), 1462\u20131505 (2006)","journal-title":"Ann. Appl. Probab."},{"issue":"1","key":"9986_CR4","first-page":"310","volume":"18","author":"YF Atchad\u00e9","year":"2017","unstructured":"Atchad\u00e9, Y.F., Fort, G., Moulines, E.: On perturbed proximal gradient algorithms. J. Mach. Learn. Res 18(1), 310\u2013342 (2017)","journal-title":"J. Mach. Learn. Res"},{"key":"9986_CR5","volume-title":"A Course in Differential Geometry. Graduate Studies in Mathematics","author":"T Aubin","year":"2000","unstructured":"Aubin, T.: A Course in Differential Geometry. Graduate Studies in Mathematics. AMS, New York (2000)"},{"key":"9986_CR6","unstructured":"Balzano, L., Nowak, R., Ellenberg, J.: Compressed sensing audio demonstration. (2010) website http:\/\/web.eecs.umich.edu\/~girasole\/csaudio"},{"key":"9986_CR7","doi-asserted-by":"crossref","unstructured":"Benveniste, A., M\u00e9tivier, M., Priouret, P.: Adaptive algorithms and stochastic approximations, volume 22 of Applications of Mathematics (New York). Springer-Verlag, Berlin, (1990). Translated from the French by Stephen S. Wilson","DOI":"10.1007\/978-3-642-75894-2"},{"key":"9986_CR8","volume-title":"Statistical inference","author":"R Berger","year":"2002","unstructured":"Berger, R., Casella, G.: Statistical inference, 2nd edn. Duxbury \/ Thomson Learning, Pacific Grove, USA (2002)","edition":"2"},{"issue":"3","key":"9986_CR9","doi-asserted-by":"publisher","first-page":"334","DOI":"10.1057\/palgrave.jors.2600425","volume":"48","author":"DP Bertsekas","year":"1997","unstructured":"Bertsekas, D.P.: Nonlinear programming. Journal of the Operational Research Society 48(3), 334\u2013334 (1997)","journal-title":"Journal of the Operational Research Society"},{"key":"9986_CR10","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511804441","volume-title":"Convex Optimization","author":"S Boyd","year":"2004","unstructured":"Boyd, S., Vandenberghe, L.: Convex Optimization. Cambridge University Press, Cambridge (2004)"},{"key":"9986_CR11","doi-asserted-by":"crossref","unstructured":"Cand\u00e8s, E.J. et al.: Compressive sampling. In: Proceedings of the international congress of mathematicians, volume 3, pages 1433\u20131452. Madrid, Spain, (2006)","DOI":"10.4171\/022-3\/69"},{"issue":"2","key":"9986_CR12","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1109\/MSP.2007.914731","volume":"25","author":"EJ Cand\u00e8s","year":"2008","unstructured":"Cand\u00e8s, E.J., Wakin, M.B.: An introduction to compressive sampling [a sensing\/sampling paradigm that goes against the common knowledge in data acquisition]. IEEE Signal Processing Magazine 25(2), 21\u201330 (2008)","journal-title":"IEEE Signal Processing Magazine"},{"issue":"452","key":"9986_CR13","doi-asserted-by":"publisher","first-page":"1286","DOI":"10.1080\/01621459.2000.10474331","volume":"95","author":"BP Carlin","year":"2000","unstructured":"Carlin, B.P., Louis, T.A.: Empirical Bayes: past, present and future. J. Am. Statist. Assoc. 95(452), 1286\u20131289 (2000)","journal-title":"J. Am. Statist. Assoc."},{"issue":"2","key":"9986_CR14","doi-asserted-by":"crossref","first-page":"83","DOI":"10.1080\/00031305.1985.10479400","volume":"39","author":"G Casella","year":"1985","unstructured":"Casella, G.: An introduction to empirical Bayes data analysis. Am. Statist. 39(2), 83\u201387 (1985)","journal-title":"Am. Statist."},{"key":"9986_CR15","doi-asserted-by":"publisher","first-page":"161","DOI":"10.1017\/S096249291600009X","volume":"25","author":"A Chambolle","year":"2016","unstructured":"Chambolle, A., Pock, T.: An introduction to continuous optimization for imaging. Acta Numerica 25, 161\u2013319 (2016)","journal-title":"Acta Numerica"},{"key":"9986_CR16","unstructured":"Cheng, X., Bartlett, P.: Convergence of langevin mcmc in kl-divergence. (2017). arXiv preprint arXiv:1705.09048"},{"key":"9986_CR17","unstructured":"Cheng, X., Chatterji, N.S., Abbasi-Yadkori, Y., Bartlett, P.L., Jordan, M.I.: Sharp convergence rates for langevin dynamics in the nonconvex setting. (2018). arXiv preprint arXiv:1805.01648"},{"key":"9986_CR18","unstructured":"Dalalyan, A.S.: Further and stronger analogy between sampling and optimization: Langevin monte carlo and gradient descent. (2017). arXiv preprint arXiv:1704.04752"},{"issue":"3","key":"9986_CR19","doi-asserted-by":"publisher","first-page":"651","DOI":"10.1111\/rssb.12183","volume":"79","author":"AS Dalalyan","year":"2017","unstructured":"Dalalyan, A.S.: Theoretical guarantees for approximate sampling from smooth and log-concave densities. J. R. Stat. Soc. Ser. B. Stat. Methodol. 79(3), 651\u2013676 (2017)","journal-title":"J. R. Stat. Soc. Ser. B. Stat. Methodol."},{"key":"9986_CR20","unstructured":"Dalalyan, A.S., Riou-Durand, L.: On sampling from a log-concave density using kinetic langevin diffusions. (2018). arXiv preprint arXiv:1807.09382"},{"key":"9986_CR21","unstructured":"De Bortoli, V., Durmus, A.: Convergence of diffusions and their discretizations:from continuous to discrete processes and back. (2019). arXiv preprint arXiv:1904.09808"},{"key":"9986_CR22","unstructured":"De\u00a0Bortoli, V., Durmus, A., Pereyra, M., Fernandez\u00a0Vida, A.: Supplement to: Efficient stochastic optimisation by unadjusted langevin monte carlo. application to maximum marginal likelihood and empirical bayesian estimation. (2019)"},{"key":"9986_CR23","doi-asserted-by":"publisher","unstructured":"De\u00a0Bortoli, V., Durmus, A., Pereyra, M., Vidal, A.F.: Maximum likelihood estimation of regularisation parameters in high-dimensional inverse problems: an empirical bayesian approach part ii: Theoretical analysis. SIAM J. Imaging Sci. 13(4):1990\u20132028 (2020a). https:\/\/doi.org\/10.1137\/20M1339842","DOI":"10.1137\/20M1339842"},{"key":"9986_CR24","doi-asserted-by":"crossref","unstructured":"De\u00a0Bortoli, V., Durmus, A., Vidal, A.F., Pereyra, M.: Maximum likelihood estimation of regularisation parameters in high-dimensional inverse problems: an empirical bayesian approach. part ii: Theoretical analysis. arXiv preprint arXiv:2008.05793, (2020b)","DOI":"10.1137\/20M1339842"},{"issue":"1","key":"9986_CR25","doi-asserted-by":"publisher","first-page":"94","DOI":"10.1214\/aos\/1018031103","volume":"27","author":"B Delyon","year":"1999","unstructured":"Delyon, B., Lavielle, M., Moulines, E.: Convergence of a stochastic approximation version of the em algorithm. Ann. Statist. 27(1), 94\u2013128 (1999)","journal-title":"Ann. Statist."},{"issue":"1","key":"9986_CR26","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1111\/j.2517-6161.1977.tb01600.x","volume":"39","author":"AP Dempster","year":"1977","unstructured":"Dempster, A.P., Laird, N.M., Rubin, D.B.: Maximum likelihood from incomplete data via the EM algorithm. J. Roy. Stat. Soc. Ser. B 39(1), 1\u201338 (1977)","journal-title":"J. Roy. Stat. Soc. Ser. B"},{"key":"9986_CR27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-97704-1","volume-title":"Markov Chains","author":"R Douc","year":"2018","unstructured":"Douc, R., Moulines, E., Priouret, P., Soulier, P.: Markov Chains. Springer, Berlin (2018). to be published"},{"key":"9986_CR28","first-page":"2121","volume":"12","author":"J Duchi","year":"2011","unstructured":"Duchi, J., Hazan, E., Singer, Y.: Adaptive subgradient methods for online learning and stochastic optimization. J. Mach. Learn. Res. 12, 2121\u20132159 (2011)","journal-title":"J. Mach. Learn. Res."},{"issue":"3","key":"9986_CR29","doi-asserted-by":"publisher","first-page":"1551","DOI":"10.1214\/16-AAP1238","volume":"27","author":"A Durmus","year":"2017","unstructured":"Durmus, A., Moulines, E.: Nonasymptotic convergence analysis for the unadjusted Langevin algorithm. Ann. Appl. Probab. 27(3), 1551\u20131587 (2017)","journal-title":"Ann. Appl. Probab."},{"issue":"1","key":"9986_CR30","doi-asserted-by":"publisher","first-page":"473","DOI":"10.1137\/16M1108340","volume":"11","author":"A Durmus","year":"2018","unstructured":"Durmus, A., Moulines, E., Pereyra, M.: Efficient bayesian computation by proximal markov chain monte carlo: when langevin meets moreau. SIAM J. Imaging Sci. 11(1), 473\u2013506 (2018)","journal-title":"SIAM J. Imaging Sci."},{"key":"9986_CR31","unstructured":"Durmus, A., Moulines, E., Saksman, E.: On the convergence of hamiltonian monte carlo. arXiv preprint arXiv:1705.00166 (2017)"},{"issue":"3\u20134","key":"9986_CR32","doi-asserted-by":"publisher","first-page":"851","DOI":"10.1007\/s00440-015-0673-1","volume":"166","author":"A Eberle","year":"2016","unstructured":"Eberle, A.: Reflection couplings and contraction rates for diffusions. Probab. Theory Related Fields 166(3\u20134), 851\u2013886 (2016)","journal-title":"Probab. Theory Related Fields"},{"key":"9986_CR33","unstructured":"Eberle, A., Guillin, A., Zimmer, R.: Couplings and quantitative contraction rates for langevin dynamics. arXiv preprint arXiv:1703.01617 (2017)"},{"key":"9986_CR34","doi-asserted-by":"crossref","unstructured":"Eberle, A., Majka, M.B.: Quantitative contraction rates for markov chains on general state spaces. arXiv preprint arXiv:1808.07033 (2018)","DOI":"10.1214\/19-EJP287"},{"issue":"4","key":"9986_CR35","doi-asserted-by":"publisher","first-page":"586","DOI":"10.1109\/JSTSP.2007.910281","volume":"1","author":"MA Figueiredo","year":"2007","unstructured":"Figueiredo, M.A., Nowak, R.D., Wright, S.J.: Gradient projection for sparse reconstruction: Application to compressed sensing and other inverse problems. IEEE J. Selected Topics Signal Process. 1(4), 586\u2013597 (2007)","journal-title":"IEEE J. Selected Topics Signal Process."},{"issue":"4","key":"9986_CR36","doi-asserted-by":"publisher","first-page":"1220","DOI":"10.1214\/aos\/1059655912","volume":"31","author":"G Fort","year":"2003","unstructured":"Fort, G., Moulines, E.: Convergence of the Monte Carlo expectation maximization for curved exponential families. Ann. Statist. 31(4), 1220\u20131259 (2003)","journal-title":"Ann. Statist."},{"issue":"6","key":"9986_CR37","doi-asserted-by":"publisher","first-page":"3262","DOI":"10.1214\/11-AOS938","volume":"39","author":"G Fort","year":"2011","unstructured":"Fort, G., Moulines, E., Priouret, P.: Convergence of adaptive and interacting Markov chain Monte Carlo algorithms. Ann. Statist. 39(6), 3262\u20133289 (2011)","journal-title":"Ann. Statist."},{"key":"9986_CR38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-21551-3","volume-title":"Handbook of Computational Statistics: Concepts and Methods","author":"JE Gentle","year":"2012","unstructured":"Gentle, J.E., H\u00e4rdle, W.K., Mori, Y.: Handbook of Computational Statistics: Concepts and Methods. Springer Science & Business Media, Berlin (2012)"},{"issue":"2","key":"9986_CR39","doi-asserted-by":"publisher","first-page":"123","DOI":"10.1111\/j.1467-9868.2010.00765.x","volume":"73","author":"M Girolami","year":"2011","unstructured":"Girolami, M., Calderhead, B.: Riemann manifold langevin and hamiltonian monte carlo methods. J. Royal Stat. Soc.: Ser. B (Stat. Methodol.) 73(2), 123\u2013214 (2011)","journal-title":"J. Royal Stat. Soc.: Ser. B (Stat. Methodol.)"},{"key":"9986_CR40","doi-asserted-by":"publisher","unstructured":"Hairer, M., Mattingly, J.C.: Yet another look at harris\u2019 ergodic theorem for markov chains. In: Seminar on Stochastic Analysis, Random Fields and Applications Vol. 63. pp. 109\u2013117. Birkh\u00e4user\/Springer Basel AG, Basel (2011). https:\/\/doi.org\/10.1007\/978-3-0348-0021-1_7","DOI":"10.1007\/978-3-0348-0021-1_7"},{"issue":"2","key":"9986_CR41","doi-asserted-by":"publisher","first-page":"341","DOI":"10.1016\/S0304-4149(99)00082-4","volume":"85","author":"SF Jarner","year":"2000","unstructured":"Jarner, S.F., Hansen, E.: Geometric ergodicity of metropolis algorithms. Stoch. Process. Their Appl. 85(2), 341\u2013361 (2000)","journal-title":"Stoch. Process. Their Appl."},{"key":"9986_CR42","volume-title":"Foundations of Modern Probability","author":"O Kallenberg","year":"2006","unstructured":"Kallenberg, O.: Foundations of Modern Probability. Springer Science & Business Media, Berlin (2006)"},{"key":"9986_CR43","unstructured":"Karimi, B., Miasojedow, B., Moulines, \u00c9., Wai, H.-T.: Non-asymptotic analysis of biased stochastic approximation scheme. arXiv preprint arXiv:1902.00629 (2019)"},{"issue":"4","key":"9986_CR44","doi-asserted-by":"publisher","first-page":"606","DOI":"10.1109\/JSTSP.2007.910971","volume":"1","author":"S-J Kim","year":"2007","unstructured":"Kim, S.-J., Koh, K., Lustig, M., Boyd, S., Gorinevsky, D.: A method for large-scale l1-regularized least squares. IEEE J. Selected Topics Signal Process. 1(4), 606\u2013617 (2007)","journal-title":"IEEE J. Selected Topics Signal Process."},{"key":"9986_CR45","volume-title":"Stochastic Approximation and Recursive Algorithms and Applications. volume\u00a035 of Applications of Mathematics (New York): Stochastic Modelling and Applied Probability","author":"HJ Kushner","year":"2003","unstructured":"Kushner, H.J., Yin, G.G.: Stochastic Approximation and Recursive Algorithms and Applications. volume\u00a035 of Applications of Mathematics (New York): Stochastic Modelling and Applied Probability, 2nd edn. Springer-Verlag, New York (2003)","edition":"2"},{"key":"9986_CR46","unstructured":"Lee, H., Risteski, A., Ge, R.: Beyond log-concavity: Provable guarantees for sampling multi-modal distributions using simulated tempering langevin monte carlo. In:Bengio, S., Wallach, H., Larochelle, H., Grauman, K., Cesa-Bianchi, N., Garnett, R. (Eds.) Advances in Neural Information Processing Systems, Curran Associates, Inc. Vol. 31. pp. 7847\u20137856 (2018). https:\/\/proceedings.neurips.cc\/paper\/2018\/file\/c6ede20e6f597abf4b3f6bb30cee16c7-Paper.pdf"},{"key":"9986_CR47","doi-asserted-by":"crossref","unstructured":"Lingala, S.G., Jacob, M.: A blind compressive sensing frame work for accelerated dynamic mri. In: 2012 9th IEEE International Symposium on Biomedical Imaging (ISBI), pp. 1060\u20131063. IEEE (2012)","DOI":"10.1109\/ISBI.2012.6235741"},{"key":"9986_CR48","unstructured":"Ma, Y.-A., Chatterji, N., Cheng, X., Flammarion, N., Bartlett, P., Jordan, M.\u00a0I.: Is there an analog of nesterov acceleration for mcmc? arXiv preprint arXiv:1902.00996 (2019)"},{"key":"9986_CR49","unstructured":"Maddison, C.J., Paulin, D., Teh, Y.\u00a0W., O\u2019Donoghue, B., Doucet, A.: Hamiltonian Descent Methods. arXiv preprint arXiv:1809.05042 (2018)"},{"issue":"3","key":"9986_CR50","doi-asserted-by":"publisher","first-page":"542","DOI":"10.2307\/1427479","volume":"24","author":"SP Meyn","year":"1992","unstructured":"Meyn, S.P., Tweedie, R.L.: Stability of Markovian processes. I. Criteria for discrete-time chains. Adv. in Appl. Probab. 24(3), 542\u2013574 (1992)","journal-title":"Adv. in Appl. Probab."},{"key":"9986_CR51","volume-title":"Handbook of Convex Optimization Methods in Imaging Science","author":"V Monga","year":"2017","unstructured":"Monga, V.: Handbook of Convex Optimization Methods in Imaging Science. Springer, Berlin (2017)"},{"key":"9986_CR52","unstructured":"Muehlebach, M., Jordan, M.\u00a0I.: A dynamical systems perspective on nesterov acceleration. arXiv preprint arXiv:1905.07436 (2019)"},{"issue":"4","key":"9986_CR53","doi-asserted-by":"publisher","first-page":"1574","DOI":"10.1137\/070704277","volume":"19","author":"A Nemirovski","year":"2008","unstructured":"Nemirovski, A., Juditsky, A., Lan, G., Shapiro, A.: Robust stochastic approximation approach to stochastic programming. SIAM J. Optim. 19(4), 1574\u20131609 (2008)","journal-title":"SIAM J. Optim."},{"key":"9986_CR54","unstructured":"Patterson, S., Teh, Y.\u00a0W.: Stochastic gradient riemannian langevin dynamics on the probability simplex. In: Advances in neural information processing systems, pp. 3102\u20133110 (2013)"},{"issue":"504","key":"9986_CR55","doi-asserted-by":"publisher","first-page":"1339","DOI":"10.1080\/01621459.2013.829001","volume":"108","author":"NG Polson","year":"2013","unstructured":"Polson, N.G., Scott, J.G., Windle, J.: Bayesian inference for logistic models using p\u00f3lya-gamma latent variables. J. Am. Stat. Assoc. 108(504), 1339\u20131349 (2013)","journal-title":"J. Am. Stat. Assoc."},{"key":"9986_CR56","doi-asserted-by":"crossref","unstructured":"P\u00f3lya, G., Szeg\u0151, G.: Problems and theorems in analysis. I. Classics in Mathematics. Springer-Verlag, Berlin, (1998). Series, integral calculus, theory of functions, Translated from the German by Dorothee Aeppli, Reprint of the 1978 English translation","DOI":"10.1007\/978-3-642-61905-2"},{"key":"9986_CR57","doi-asserted-by":"publisher","first-page":"400","DOI":"10.1214\/aoms\/1177729586","volume":"22","author":"H Robbins","year":"1951","unstructured":"Robbins, H., Monro, S.: A stochastic approximation method. Ann. Math. Stat. 22, 400\u2013407 (1951)","journal-title":"Ann. Math. Stat."},{"key":"9986_CR58","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4757-4145-2","volume-title":"Monte Carlo Statistical Methods","author":"CP Robert","year":"2004","unstructured":"Robert, C.P., Casella, G.: Monte Carlo Statistical Methods, 2nd edn. Springer-Verlag, New York (2004)","edition":"2"},{"key":"9986_CR59","doi-asserted-by":"crossref","unstructured":"Robert C.\u00a0P., Wraith, D.: Computational methods for bayesian model choice. In: Aip Conference Proceedings, vol. 1193, pp. 251\u2013262. AIP (2009)","DOI":"10.1063\/1.3275622"},{"issue":"4","key":"9986_CR60","doi-asserted-by":"publisher","first-page":"341","DOI":"10.2307\/3318418","volume":"2","author":"GO Roberts","year":"1996","unstructured":"Roberts, G.O., Tweedie, R.L.: Exponential convergence of Langevin distributions and their discrete approximations. Bernoulli 2(4), 341\u2013363 (1996)","journal-title":"Bernoulli"},{"issue":"1","key":"9986_CR61","first-page":"193","volume":"17","author":"YW Teh","year":"2016","unstructured":"Teh, Y.W., Thiery, A.H., Vollmer, S.J.: Consistency and fluctuations for stochastic gradient langevin dynamics. J. Mach. Learn. Res. 17(1), 193\u2013225 (2016)","journal-title":"J. Mach. Learn. Res."},{"key":"9986_CR62","doi-asserted-by":"publisher","unstructured":"Tierney, L. Markov chains for exploring posterior distributions. Ann. Statist. 22(4):1701\u20131762 (1994). https:\/\/doi.org\/10.1214\/aos\/1176325750","DOI":"10.1214\/aos\/1176325750"},{"key":"9986_CR63","doi-asserted-by":"crossref","unstructured":"Vidal, A.F., Bortoli, V.\u00a0D., Pereyra, M., Durmus, A.: Maximum likelihood estimation of regularisation parameters in high-dimensional inverse problems: an empirical bayesian approach. part i: Methodology and experiments (2019)","DOI":"10.1137\/20M1339829"},{"key":"9986_CR64","doi-asserted-by":"crossref","unstructured":"Vidal, A.F., Pereyra, M.: Maximum likelihood estimation of regularisation parameters. In: 2018 25th IEEE International Conference on Image Processing (ICIP), pp. 1742\u20131746. IEEE (2018)","DOI":"10.1109\/ICIP.2018.8451795"},{"issue":"1","key":"9986_CR65","first-page":"5504","volume":"17","author":"SJ Vollmer","year":"2016","unstructured":"Vollmer, S.J., Zygalakis, K.C., Teh, Y.W.: Exploration of the (non-) asymptotic bias and variance of stochastic gradient langevin dynamics. J. Mach. Learn. Res. 17(1), 5504\u20135548 (2016)","journal-title":"J. Mach. Learn. Res."},{"key":"9986_CR66","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4419-0925-1","volume-title":"Bayesian and Frequentist Regression Methods","author":"J Wakefield","year":"2013","unstructured":"Wakefield, J.: Bayesian and Frequentist Regression Methods. Springer Science & Business Media, Berlin (2013)"},{"key":"9986_CR67","unstructured":"Welling, M., Teh, Y.\u00a0W.: Bayesian learning via stochastic gradient langevin dynamics. In: Proceedings of the 28th international Conference on Machine Learning (ICML-11), pp. 681\u2013688 (2011a)"},{"key":"9986_CR68","unstructured":"Welling, M., Teh, Y.\u00a0W.: Bayesian learning via stochastic gradient Langevin dynamics. In: Proceedings of the International Conference on Machine Learning, pp. 681\u2013688 (2011b)"}],"container-title":["Statistics and Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11222-020-09986-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11222-020-09986-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11222-020-09986-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,26]],"date-time":"2024-08-26T10:55:04Z","timestamp":1724669704000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11222-020-09986-y"}},"subtitle":["Application to maximum marginal likelihood and empirical Bayesian estimation"],"short-title":[],"issued":{"date-parts":[[2021,3,19]]},"references-count":68,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2021,5]]}},"alternative-id":["9986"],"URL":"https:\/\/doi.org\/10.1007\/s11222-020-09986-y","relation":{},"ISSN":["0960-3174","1573-1375"],"issn-type":[{"value":"0960-3174","type":"print"},{"value":"1573-1375","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,3,19]]},"assertion":[{"value":"26 December 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 September 2020","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 March 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"29"}}