{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,16]],"date-time":"2026-11-16T19:20:46Z","timestamp":1794856846489,"version":"4.9.1"},"reference-count":98,"publisher":"Society for Industrial & Applied Mathematics (SIAM)","issue":"1","funder":[{"DOI":"10.13039\/100000181","name":"Air Force Office of Scientific Research","doi-asserted-by":"publisher","award":["FA9550-18-1-0502"],"award-info":[{"award-number":["FA9550-18-1-0502"]}],"id":[{"id":"10.13039\/100000181","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000159","name":"Division of Atmospheric and Geospace Sciences","doi-asserted-by":"publisher","award":["AGS-1835860"],"award-info":[{"award-number":["AGS-1835860"]}],"id":[{"id":"10.13039\/100000159","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000121","name":"Division of Mathematical Sciences","doi-asserted-by":"publisher","award":["DMS-1818977"],"award-info":[{"award-number":["DMS-1818977"]}],"id":[{"id":"10.13039\/100000121","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["SIAM J. Appl. Dyn. Syst."],"published-print":{"date-parts":[[2020,1]]},"abstract":"<jats:p>Solving inverse problems without the use of derivatives or adjoints of the forward model is highly desirable in many applications arising in science and engineering. In this paper we propose a new version of such a methodology, a framework for its analysis, and numerical evidence of the practicality of the method proposed. Our starting point is an ensemble of overdamped Langevin diffusions which interact through a single preconditioner computed as the empirical ensemble covariance. We demonstrate that the nonlinear Fokker--Planck equation arising from the mean-field limit of the associated stochastic differential equation (SDE) has a novel gradient flow structure, built on the Wasserstein metric and the covariance matrix of the noisy flow. Using this structure, we investigate large time properties of the Fokker--Planck equation, showing that its invariant measure coincides with that of a single Langevin diffusion, and demonstrating exponential convergence to the invariant measure in a number of settings. We introduce a new noisy variant on ensemble Kalman inversion (EKI) algorithms found from the original SDE by replacing exact gradients with ensemble differences; this defines the ensemble Kalman sampler (EKS). Numerical results are presented which demonstrate its efficacy as a derivative-free approximate sampler for the Bayesian posterior arising from inverse problems.<\/jats:p>","DOI":"10.1137\/19m1251655","type":"journal-article","created":{"date-parts":[[2020,2,4]],"date-time":"2020-02-04T12:46:45Z","timestamp":1580820405000},"page":"412-441","source":"Crossref","is-referenced-by-count":145,"title":["Interacting Langevin Diffusions: Gradient Structure and Ensemble Kalman Sampler"],"prefix":"10.1137","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3279-619X","authenticated-orcid":true,"given":"Alfredo","family":"Garbuno-Inigo","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Franca","family":"Hoffmann","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2218-5734","authenticated-orcid":true,"given":"Wuchen","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andrew M.","family":"Stuart","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"351","published-online":{"date-parts":[[2020,2,4]]},"reference":[{"key":"atypb1","unstructured":"L. Ambrosio, N. Gigli, and G. Savar\u00e9,\n                      Gradient Flows: In Metric Spaces and in the Space of Probability Measures\n                      , Birkh\u00e4user, Basel, 2005."},{"key":"atypb2","doi-asserted-by":"publisher","DOI":"10.1081\/PDE-100002246"},{"key":"atypb3","unstructured":"N. Ay, J. Jost, H. V. L\u00ea, and L. J. Schwachh\u00f6fer,\n                      Information Geometry\n                      , Ergeb. Math. Grenzgeb. (3), A Series of Modern Surveys in Mathematics [Results in Mathematics and Related Areas], 3rd Series, A Series of Modern Surveys in Mathematics 64, Springer, Cham, 2017."},{"key":"atypb4","first-page":"84","author":"Bakry D.","year":"1983","journal-title":"S\u00e9minaire de Probabilit\u00e9s"},{"key":"atypb5","doi-asserted-by":"publisher","DOI":"10.1016\/j.spa.2007.12.005"},{"key":"atypb6","doi-asserted-by":"publisher","DOI":"10.1214\/105051607000000096"},{"key":"atypb7","doi-asserted-by":"publisher","DOI":"10.1002\/cjs.5550360401"},{"key":"atypb8","doi-asserted-by":"publisher","DOI":"10.1002\/qj.672"},{"key":"atypb9","doi-asserted-by":"publisher","DOI":"10.1002\/qj.672"},{"key":"atypb10","doi-asserted-by":"publisher","DOI":"10.1127\/0941-2948\/2012\/0307"},{"key":"atypb11","doi-asserted-by":"publisher","DOI":"10.1002\/wcc.535"},{"key":"atypb12","doi-asserted-by":"publisher","DOI":"10.1142\/S0218202518500276"},{"key":"atypb13","first-page":"297","author":"Carrillo J. A.","year":"2010","journal-title":"MA"},{"key":"atypb14","doi-asserted-by":"publisher","DOI":"10.1002\/(SICI)1099-1476(19980910)21:13<1269::AID-MMA995>3.0.CO;2-O"},{"key":"atypb15","unstructured":"N. K. Chada, A. M. Stuart, and X. T. Tong,\n                      Tikhonov Regularization within Ensemble Kalman Inversion\n                      , preprint,https:\/\/arxiv.org\/abs\/1901.10382, 2019."},{"key":"atypb16","doi-asserted-by":"publisher","DOI":"10.1007\/s11004-011-9376-z"},{"key":"atypb17","doi-asserted-by":"crossref","unstructured":"E. Cleary, A. Garbuno-Inigo, S. Lan, T. Schneider, and A. M. Stuart,\n                      Calibrate, Emulate, Sample\n                      , preprint,https:\/\/arxiv.org\/abs\/2001.03689, 2020.","DOI":"10.1016\/j.jcp.2020.109716"},{"key":"atypb18","doi-asserted-by":"publisher","DOI":"10.1214\/13-STS421"},{"key":"atypb19","doi-asserted-by":"publisher","DOI":"10.1080\/17442500902723575"},{"key":"atypb20","first-page":"5920","author":"Daum F.","year":"2011","journal-title":"NJ"},{"key":"atypb21","doi-asserted-by":"publisher","DOI":"10.1137\/17M1119056"},{"key":"atypb22","doi-asserted-by":"publisher","DOI":"10.1137\/16M1087497"},{"key":"atypb23","doi-asserted-by":"publisher","DOI":"10.1214\/17-AAP1317"},{"key":"atypb24","unstructured":"G. Detommaso, T. Cui, Y. Marzouk, A. Spantini, and R. Scheichl,\n                      A Stein variational Newton method\n                      , in Proceedings of the 32nd Conference on Neural Information Processing Systems (NeurIPS 2018), Montreal, Canada, Advances in Neural Information Processing Systems 31, S. Bengio, ed., 2018, pp. 9169-9179."},{"key":"atypb25","unstructured":"Z. Ding and Q. Li,\n                      Mean-Field Limit and Numerical Analysis for Ensemble Kalman Inversion: Linear Setting\n                      , preprint,https:\/\/arxiv.org\/abs\/1908.05575v1, 2019."},{"key":"atypb26","unstructured":"A. Duncan and L. Szpruch,\n                      private communication\n                      , 2019."},{"key":"atypb27","doi-asserted-by":"publisher","DOI":"10.1007\/s10955-016-1491-2"},{"key":"atypb28","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcp.2012.07.022"},{"key":"atypb29","doi-asserted-by":"publisher","DOI":"10.1007\/s10596-012-9333-z"},{"key":"atypb30","doi-asserted-by":"crossref","unstructured":"H. W. Engl, M. Hanke, and A. Neubauer,\n                      Regularization of Inverse Problems\n                      , Math. Appl. 375, Springer Netherlands, 1996.","DOI":"10.1007\/978-94-009-1740-8"},{"key":"atypb31","doi-asserted-by":"publisher","DOI":"10.1137\/140981319"},{"key":"atypb32","doi-asserted-by":"crossref","unstructured":"G. Evensen,\n                      Data Assimilation: The Ensemble Kalman Filter\n                      , Springer-Verlag, Berlin, 2009.","DOI":"10.1007\/978-3-642-03711-5"},{"key":"atypb33","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-9868.2010.00765.x"},{"key":"atypb34","doi-asserted-by":"publisher","DOI":"10.1007\/BF02440162"},{"key":"atypb35","doi-asserted-by":"publisher","DOI":"10.2140\/camcos.2010.5.65"},{"key":"atypb36","doi-asserted-by":"publisher","DOI":"10.3934\/krm.2008.1.415"},{"key":"atypb37","doi-asserted-by":"publisher","DOI":"10.1093\/imanum\/drt031"},{"key":"atypb38","unstructured":"A. Halder and T. T. Georgiou,\n                      Gradient Flows in Filtering and Fisher-Rao Geometry\n                      , preprint,https:\/\/arxiv.org\/abs\/1710.00064, 2017."},{"key":"atypb39","unstructured":"M. Herty and G. Visconti,\n                      Kinetic Methods for Inverse Problems\n                      , preprint,https:\/\/arxiv.org\/abs\/1811.09387, 2018."},{"key":"atypb40","doi-asserted-by":"publisher","DOI":"10.1137\/0731075"},{"key":"atypb41","doi-asserted-by":"publisher","DOI":"10.1007\/s10596-014-9456-5"},{"key":"atypb42","doi-asserted-by":"publisher","DOI":"10.1088\/0266-5611\/32\/2\/025002"},{"key":"atypb43","doi-asserted-by":"publisher","DOI":"10.1088\/0266-5611\/29\/4\/045001"},{"key":"atypb44","first-page":"379","author":"Jabin P.-E.","year":"2017","journal-title":"Cham"},{"key":"atypb45","doi-asserted-by":"publisher","DOI":"10.1137\/S0036141096303359"},{"key":"atypb46","doi-asserted-by":"crossref","unstructured":"J. Kaipio and E. Somersalo,\n                      Statistical and Computational Inverse Problems\n                      , Appl. Math. Sci. 160, Springer-Verlag, New York, 2006.","DOI":"10.1007\/b138659"},{"key":"atypb47","doi-asserted-by":"publisher","DOI":"10.1115\/1.3662552"},{"key":"atypb48","doi-asserted-by":"publisher","DOI":"10.1115\/1.3658902"},{"key":"atypb49","doi-asserted-by":"publisher","DOI":"10.1088\/0951-7715\/27\/10\/2579"},{"key":"atypb50","unstructured":"N. B. Kovachki and A. M. Stuart,\n                      Ensemble Kalman Inversion: A Derivative-Free Technique for Machine Learning Tasks\n                      , preprint,https:\/\/arxiv.org\/abs\/1808.03620, 2018."},{"key":"atypb51","doi-asserted-by":"publisher","DOI":"10.1090\/S0002-9947-1988-0924776-9"},{"key":"atypb52","doi-asserted-by":"publisher","DOI":"10.1137\/13094743X"},{"key":"atypb53","doi-asserted-by":"crossref","unstructured":"K. Law, A. Stuart, and K. Zygalakis,\n                      Data Assimilation: A Mathematical Introduction\n                      , Texts Appl. Math. 62, Springer International Publishing, Switzerland, 2015.","DOI":"10.1007\/978-3-319-20325-6"},{"key":"atypb54","unstructured":"B. Leimkuhler and C. Matthews,\n                      Molecular Dynamics: With Deterministic and Stochastic Numerical Methods\n                      , Interdiscip. Appl. Math. 39, Springer International Publishing, Switzerland, 2016."},{"key":"atypb55","doi-asserted-by":"publisher","DOI":"10.1007\/s11222-017-9730-1"},{"key":"atypb56","doi-asserted-by":"publisher","DOI":"10.1007\/s10955-009-9734-0"},{"key":"atypb57","unstructured":"W. Li,\n                      Geometry of Probability Simplex via Optimal Transport\n                      , preprint,https:\/\/arxiv.org\/abs\/1803.06360, 2018."},{"key":"atypb58","first-page":"705","author":"Li W.","year":"2019","journal-title":"Cham"},{"key":"atypb59","unstructured":"W. Li and G. Montufar,\n                      Natural Gradient via Optimal Transport\n                      , preprint,https:\/\/arxiv.org\/abs\/1803.07033, 2018."},{"key":"atypb60","unstructured":"Q. Liu and D. Wang,\n                      Stein variational gradient descent: A general purpose Bayesian inference algorithm\n                      , in Proceedings of the 30th Conference on Neural Information Processing Systems (NIPS 2016), Barcelona, Spain, Advances in Neural Information Processing Systems 29, D. D. Lee et al., eds., 2016, pp. 2378-2386."},{"key":"atypb61","unstructured":"J. Lu, Y. Lu, and J. Nolen,\n                      Scaling Limit of the Stein Variational Gradient Descent PartI:The Mean Field Regime\n                      , preprint,https:\/\/arxiv.org\/abs\/1805.04035v1, 2018."},{"key":"atypb62","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRev.91.1512"},{"key":"atypb63","doi-asserted-by":"crossref","unstructured":"A. J. Majda and J. Harlim,\n                      Filtering Complex Turbulent Systems\n                      , Cambridge University Press, Cambridge, 2012.","DOI":"10.1017\/CBO9781139061308"},{"key":"atypb64","first-page":"1","volume":"19","author":"Markowich P. A.","year":"2000","journal-title":"Mat. Contemp."},{"key":"atypb65","first-page":"1","author":"Marzouk Y.","year":"2016","journal-title":"Cham"},{"key":"atypb66","doi-asserted-by":"publisher","DOI":"10.1214\/10-AAP754"},{"key":"atypb67","doi-asserted-by":"publisher","DOI":"10.1098\/rsta.1999.0363"},{"key":"atypb68","doi-asserted-by":"publisher","DOI":"10.1515\/jnet-2015-0073"},{"key":"atypb69","unstructured":"N. N\u00fcsken and S. Reich,\n                      Note on Interacting Langevin Diffusions: Gradient Structure and Ensemble Kalman Sampler by Garbuno-Inigo, Hoffmann, Li and Stuart\n                      , preprint,https:\/\/arxiv.org\/abs\/1908.10890, 2019."},{"key":"atypb70","doi-asserted-by":"crossref","unstructured":"D. S. Oliver, A. C. Reynolds, and N. Liu,\n                      Inverse Theory for Petroleum Reservoir Characterization and History Matching\n                      , Cambridge University Press, Cambridge, 2008.","DOI":"10.1017\/CBO9780511535642"},{"key":"atypb71","unstructured":"Y. Ollivier,\n                      Online Natural Gradient as a Kalman Filter\n                      , preprint,https:\/\/arxiv.org\/abs\/1703.00209, 2017."},{"key":"atypb72","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRev.37.405"},{"key":"atypb73","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRev.38.2265"},{"key":"atypb74","doi-asserted-by":"crossref","unstructured":"H. \u00d6ttinger,\n                      Beyond Equilibrium Thermodynamics\n                      , John Wiley & Sons, Inc., 2005,https:\/\/books.google.com\/books?id=Prh9moT1WzMC.","DOI":"10.1002\/0471727903"},{"key":"atypb75","doi-asserted-by":"publisher","DOI":"10.1081\/PDE-100002243"},{"key":"atypb76","doi-asserted-by":"publisher","DOI":"10.1088\/0951-7715\/24\/5\/013"},{"key":"atypb77","unstructured":"L. Pareschi and G. Toscani,\n                      Interacting Multiagent Systems: Kinetic Equations and Monte Carlo Methods\n                      , no. 9780199655465, OUP Catalogue, Oxford University Press, 2013,https:\/\/ideas.repec.org\/b\/oxp\/obooks\/9780199655465.html."},{"key":"atypb78","unstructured":"S. Pathiraja and S. Reich,\n                      Discrete Gradients for Computational Bayesian Inference\n                      , preprint,https:\/\/arxiv.org\/abs\/1903.00186, 2019; Comput. Dyn., to appear."},{"key":"atypb79","doi-asserted-by":"crossref","unstructured":"G. A. Pavliotis,\n                      Stochastic Processes and Applications: Diffusion Processes, the Fokker-Planck and Langevin Equations\n                      , Texts Appl. Math. 60, Springer-Verlag, New York, 2014.","DOI":"10.1007\/978-1-4939-1323-7"},{"key":"atypb80","doi-asserted-by":"publisher","DOI":"10.1007\/s40072-014-0029-3"},{"key":"atypb81","doi-asserted-by":"publisher","DOI":"10.1007\/s10543-010-0302-4"},{"key":"atypb82","doi-asserted-by":"publisher","DOI":"10.1137\/130907367"},{"key":"atypb83","unstructured":"S. Reich,\n                      Data Assimilation: The Schr\u00f6dinger Perspective\n                      , preprint,https:\/\/arxiv.org\/abs\/1807.08351, 2018."},{"key":"atypb84","doi-asserted-by":"crossref","unstructured":"S. Reich and C. Cotter,\n                      Probabilistic Forecasting and Bayesian Data Assimilation\n                      , Cambridge University Press, Cambridge, 2015.","DOI":"10.1017\/CBO9781107706804"},{"key":"atypb85","doi-asserted-by":"publisher","DOI":"10.1214\/aoap\/1034625254"},{"key":"atypb86","doi-asserted-by":"publisher","DOI":"10.1111\/1467-9868.00123"},{"key":"atypb87","doi-asserted-by":"publisher","DOI":"10.1214\/ss\/1015346320"},{"key":"atypb88","doi-asserted-by":"publisher","DOI":"10.1080\/00036811.2017.1386784"},{"key":"atypb89","doi-asserted-by":"publisher","DOI":"10.1137\/16M105959X"},{"key":"atypb90","doi-asserted-by":"publisher","DOI":"10.1002\/2017GL076101"},{"key":"atypb91","doi-asserted-by":"publisher","DOI":"10.1111\/1467-9868.00353"},{"key":"atypb92","first-page":"165","author":"Sznitman A.-S.","year":"1991","journal-title":"Berlin"},{"key":"atypb93","doi-asserted-by":"publisher","DOI":"10.1115\/1.4037780"},{"key":"atypb94","unstructured":"A. Tong Lin, W. Li, S. Osher, and G. Mont\u00fafar,\n                      Wasserstein Proximal of GANS\n                      , CAM report 18-53, Department of Mathematics, University of California, Los Angeles, 2019."},{"key":"atypb95","doi-asserted-by":"publisher","DOI":"10.4310\/CMS.2006.v4.n3.a1"},{"key":"atypb96","doi-asserted-by":"crossref","unstructured":"C. Villani,\n                      Optimal Transport: Old and New\n                      , Grundlehren Math. Wiss. 338, Springer, Berlin, 2009.","DOI":"10.1007\/978-3-540-71050-9"},{"key":"atypb97","unstructured":"J. Yang, G. O. Roberts, and J. S. Rosenthal,\n                      Optimal Scaling of Metropolis Algorithms on General Target Distributions\n                      , preprint,https:\/\/arxiv.org\/abs\/1904.12157, 2019."},{"key":"atypb98","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2013.2258825"}],"container-title":["SIAM Journal on Applied Dynamical Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/epubs.siam.org\/doi\/pdf\/10.1137\/19M1251655","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,20]],"date-time":"2026-08-20T14:07:40Z","timestamp":1787234860000},"score":1,"resource":{"primary":{"URL":"https:\/\/epubs.siam.org\/doi\/10.1137\/19M1251655"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,1]]},"references-count":98,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2020,1]]}},"alternative-id":["10.1137\/19M1251655"],"URL":"https:\/\/doi.org\/10.1137\/19m1251655","relation":{},"ISSN":["1536-0040"],"issn-type":[{"value":"1536-0040","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,1]]}}}