{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T22:46:45Z","timestamp":1790808405197,"version":"4.1.0"},"reference-count":59,"publisher":"Oxford University Press (OUP)","issue":"4","license":[{"start":{"date-parts":[[2023,3,9]],"date-time":"2023-03-09T00:00:00Z","timestamp":1678320000000},"content-version":"vor","delay-in-days":324,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,9,1]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Bayesian inference for nonlinear diffusions, observed at discrete times, is a challenging task that has prompted the development of a number of algorithms, mainly within the computational statistics community. We propose a new direction, and accompanying methodology\u2014borrowing ideas from statistical physics and computational chemistry\u2014for inferring the posterior distribution of latent diffusion paths and model parameters, given observations of the process. Joint configurations of the underlying process noise and of parameters, mapping onto diffusion paths consistent with observations, form an implicitly defined manifold. Then, by making use of a constrained Hamiltonian Monte Carlo algorithm on the embedded manifold, we are able to perform computationally efficient inference for a class of discretely observed diffusion models. Critically, in contrast with other approaches proposed in the literature, our methodology is highly automated, requiring minimal user intervention and applying alike in a range of settings, including: elliptic or hypo-elliptic systems; observations with or without noise; linear or non-linear observation operators. Exploiting Markovianity, we propose a variant of the method with complexity that scales linearly in the resolution of path discretisation and the number of observation times. Python code reproducing the results is available at http:\/\/doi.org\/10.5281\/zenodo.5796148.<\/jats:p>","DOI":"10.1111\/rssb.12497","type":"journal-article","created":{"date-parts":[[2022,4,19]],"date-time":"2022-04-19T17:57:54Z","timestamp":1650391074000},"page":"1229-1256","source":"Crossref","is-referenced-by-count":20,"title":["Manifold Markov Chain Monte Carlo Methods for Bayesian Inference in Diffusion Models"],"prefix":"10.1093","volume":"84","author":[{"given":"Matthew M.","family":"Graham","sequence":"first","affiliation":[{"name":"University College London , London , UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alexandre H.","family":"Thiery","sequence":"additional","affiliation":[{"name":"National University of Singapore Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alexandros","family":"Beskos","sequence":"additional","affiliation":[{"name":"University College London , London , UK"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2022,4,19]]},"reference":[{"key":"2023030906302096500_","doi-asserted-by":"crossref","first-page":"24","DOI":"10.1016\/0021-9991(83)90014-1","article-title":"RATTLE: a \u2018velocity\u2019 version of the SHAKE algorithm for molecular dynamics calculations","volume":"52","author":"Andersen","year":"1983","journal-title":"Journal of Computational Physics"},{"key":"2023030906302096500_","doi-asserted-by":"crossref","first-page":"586","DOI":"10.1136\/bmj.1.6112.586","article-title":"News and Notes: influenza in a boarding school","volume":"1","author":"Anonymous","year":"1978","journal-title":"British Medical Journal"},{"key":"2023030906302096500_","volume-title":"Mathematical methods of classical mechanics","author":"Arnol'd","year":"2013"},{"key":"2023030906302096500_","author":"Barp","year":"2020"},{"key":"2023030906302096500_","doi-asserted-by":"crossref","first-page":"46","DOI":"10.1016\/j.spl.2014.03.016","article-title":"A stable manifold MCMC method for high dimensions","volume":"90","author":"Beskos","year":"2014","journal-title":"Statistics & Probability Letters"},{"key":"2023030906302096500_","doi-asserted-by":"crossref","first-page":"2201","DOI":"10.1016\/j.spa.2011.06.003","article-title":"Hybrid Monte Carlo on Hilbert spaces","volume":"121","author":"Beskos","year":"2011","journal-title":"Stochastic Processes and their Applications"},{"key":"2023030906302096500_","doi-asserted-by":"crossref","first-page":"1415","DOI":"10.1016\/j.spa.2012.12.001","article-title":"Advanced MCMC methods for sampling on diffusion pathspace","volume":"123","author":"Beskos","year":"2013","journal-title":"Stochastic Processes and their Applications"},{"key":"2023030906302096500_","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":"2023030906302096500_","doi-asserted-by":"crossref","first-page":"327","DOI":"10.1016\/j.jcp.2016.12.041","article-title":"Geometric MCMC for infinite-dimensional inverse problems","volume":"335","author":"Beskos","year":"2017","journal-title":"Journal of Computational Physics"},{"key":"2023030906302096500_","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":"2023030906302096500_","volume-title":"A conceptual introduction to Hamiltonian Monte Carlo","author":"Betancourt","year":"2017"},{"key":"2023030906302096500_","first-page":"30","article-title":"Hamiltonian Monte Carlo for hierarchical models","volume":"79","author":"Betancourt","year":"2015","journal-title":"Current trends in Bayesian methodology with applications"},{"key":"2023030906302096500_","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1137\/141000671","article-title":"Julia: a fresh approach to numerical computing","volume":"59","author":"Bezanson","year":"2017","journal-title":"SIAM review"},{"key":"2023030906302096500_","doi-asserted-by":"crossref","first-page":"173","DOI":"10.1017\/apr.2019.54","article-title":"Simulation of elliptic and hypo-elliptic conditional diffusions","volume":"52","author":"Bierkens","year":"2020","journal-title":"Advances in Applied Probability"},{"key":"2023030906302096500_","volume-title":"JAX: composable transformations of Python+NumPy programs","author":"Bradbury","year":"2018"},{"key":"2023030906302096500_","volume-title":"A family of MCMC methods on implicitly defined manifolds","author":"Brubaker","year":"2012"},{"key":"2023030906302096500_","volume-title":"Likelihood based inference for diffusion driven models","author":"Chib","year":"2004"},{"key":"2023030906302096500_","doi-asserted-by":"crossref","DOI":"10.1214\/12-IMSCOLL1006","volume-title":"Sampling from a manifold","author":"Diaconis","year":"2013"},{"key":"2023030906302096500_","doi-asserted-by":"crossref","first-page":"361","DOI":"10.1111\/rssb.12307","article-title":"Hypoelliptic diffusions: filtering and inference from complete and partial observations","volume":"81","author":"Ditlevsen","year":"2019","journal-title":"Journal of the Royal Statistical Society: Series B (Statistical Methodology)"},{"key":"2023030906302096500_","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":"2023030906302096500_","doi-asserted-by":"crossref","first-page":"959","DOI":"10.1111\/1468-0262.00226","article-title":"Likelihood inference for discretely observed nonlinear diffusions","volume":"69","author":"Elerian","year":"2001","journal-title":"Econometrica"},{"key":"2023030906302096500_","doi-asserted-by":"crossref","first-page":"445","DOI":"10.1016\/S0006-3495(61)86902-6","article-title":"Impulses and physiological states in theoretical models of nerve membrane","volume":"1","author":"FitzHugh","year":"1961","journal-title":"Biophysical Journal"},{"key":"2023030906302096500_","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-642-25969-2","volume-title":"Inference for diffusion processes: with applications in life sciences","author":"Fuchs","year":"2013"},{"key":"2023030906302096500_","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":"Journal of the Royal Statistical Society: Series B (Statistical Methodology)"},{"key":"2023030906302096500_","doi-asserted-by":"crossref","first-page":"1674","DOI":"10.1016\/j.csda.2007.05.019","article-title":"Bayesian inference for nonlinear multivariate diffusion models observed with error","volume":"52","author":"Golightly","year":"2008","journal-title":"Computational Statistics & Data Analysis"},{"key":"2023030906302096500_","author":"Graham","year":"2019"},{"key":"2023030906302096500_","doi-asserted-by":"crossref","first-page":"5105","DOI":"10.1214\/17-EJS1340SI","article-title":"Asymptotically exact inference in differentiable generative models","volume":"11","author":"Graham","year":"2017","journal-title":"Electronic Journal of Statistics"},{"key":"2023030906302096500_","doi-asserted-by":"crossref","DOI":"10.1137\/1.9780898717761","volume-title":"Evaluating derivatives: principles and techniques of algorithmic differentiation","author":"Griewank","year":"2008"},{"key":"2023030906302096500_","doi-asserted-by":"crossref","first-page":"700","DOI":"10.1002\/zamm.200410218","article-title":"A constrained hybrid Monte-Carlo algorithm and the problem of calculating the free energy in several variables","volume":"85","author":"Hartmann","year":"2005","journal-title":"ZAMM-Journal of Applied Mathematics and Mechanics\/Zeitschrift f\u00fcr Angewandte Mathematik und Mechanik: Applied Mathematics and Mechanics"},{"key":"2023030906302096500_","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":"2023030906302096500_","doi-asserted-by":"crossref","DOI":"10.1093\/oso\/9780199212903.001.0001","volume-title":"Geometric mechanics and symmetry: from finite to infinite dimensions","author":"Holm","year":"2009"},{"key":"2023030906302096500_","doi-asserted-by":"crossref","first-page":"90","DOI":"10.1109\/MCSE.2007.55","article-title":"Matplotlib: a 2D graphics environment","volume":"9","author":"Hunter","year":"2007","journal-title":"Computing in Science & Engineering"},{"key":"2023030906302096500_","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-662-12616-5","volume-title":"Numerical Solution of Stochastic Differential Equations, vol. 23 of Stochastic Modelling and Applied Probability","author":"Kloeden","year":"1992"},{"key":"2023030906302096500_","doi-asserted-by":"crossref","first-page":"1143","DOI":"10.21105\/joss.01143","article-title":"ArviZ a unified library for exploratory analysis of Bayesian models in Python","volume":"4","author":"Kumar","year":"2019","journal-title":"Journal of Open Source Software"},{"key":"2023030906302096500_","doi-asserted-by":"crossref","first-page":"20160138","DOI":"10.1098\/rspa.2016.0138","article-title":"Efficient molecular dynamics using geodesic integration and solvent\u2013solute splitting","volume":"472","author":"Leimkuhler","year":"2016","journal-title":"Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences"},{"key":"2023030906302096500_","volume-title":"Simulating Hamiltonian dynamics, vol. 14 of Cambridge monographs on applied and computational mathematics","author":"Leimkuhler","year":"2004"},{"key":"2023030906302096500_","doi-asserted-by":"crossref","first-page":"117","DOI":"10.1006\/jcph.1994.1085","article-title":"Symplectic numerical integrators in constrained Hamiltonian systems","volume":"112","author":"Leimkuhler","year":"1994","journal-title":"Journal of Computational Physics"},{"key":"2023030906302096500_","doi-asserted-by":"crossref","first-page":"379","DOI":"10.1007\/s00211-019-01056-4","article-title":"Hybrid Monte Carlo methods for sampling probability measures on submanifolds","volume":"143","author":"Leli\u00e8vre","year":"2019","journal-title":"Numerische Mathematik"},{"key":"2023030906302096500_","doi-asserted-by":"crossref","first-page":"641","DOI":"10.1080\/17442508.2017.1381097","article-title":"Bayesian estimation of incompletely observed diffusions","volume":"90","author":"van der Meulen","year":"2018","journal-title":"Stochastics"},{"key":"2023030906302096500_","author":"van der Meulen","year":"2020"},{"key":"2023030906302096500_","volume-title":"The computational cost of blocking for sampling discretely observed diffusions","author":"Mider","year":"2020"},{"key":"2023030906302096500_","doi-asserted-by":"crossref","DOI":"10.1214\/21-EJS1894","article-title":"Continuous-discrete smoothing of diffusions","volume":"15","author":"Mider","year":"2021","journal-title":"Electronic Journal of Statistics"},{"key":"2023030906302096500_","doi-asserted-by":"crossref","first-page":"557","DOI":"10.1137\/1119062","article-title":"Approximate integration of stochastic differential equations","volume":"19","author":"Mil'shtejn","year":"1975","journal-title":"Theory of Probability & Its Applications"},{"key":"2023030906302096500_","doi-asserted-by":"crossref","first-page":"2061","DOI":"10.1109\/JRPROC.1962.288235","article-title":"An active pulse transmission line simulating nerve axon","volume":"50","author":"Nagumo","year":"1962","journal-title":"Proceedings of the IRE"},{"key":"2023030906302096500_","first-page":"139","volume-title":"Handbook of Markov Chain Monte Carlo","author":"Neal","year":"2011"},{"key":"2023030906302096500_","volume-title":"Stochastic differential equations: an introduction with applications","author":"Oksendal","year":"2013"},{"key":"2023030906302096500_","volume-title":"Non-centered parameterisations for hierarchical models and data augmentation","author":"Papaspiliopoulos","year":"2003"},{"key":"2023030906302096500_","doi-asserted-by":"crossref","first-page":"59","DOI":"10.1214\/088342307000000014","article-title":"A General Framework for the Parametrization of Hierarchical Models","volume":"22","author":"Papaspiliopoulos","year":"2007","journal-title":"Statistical Science"},{"key":"2023030906302096500_","doi-asserted-by":"crossref","first-page":"665","DOI":"10.1080\/10618600.2013.783484","article-title":"Data augmentation for diffusions","volume":"22","author":"Papaspiliopoulos","year":"2013","journal-title":"Journal of Computational and Graphical Statistics"},{"key":"2023030906302096500_","doi-asserted-by":"crossref","first-page":"475","DOI":"10.1137\/0733025","article-title":"Symplectic integration of constrained Hamiltonian systems by composition methods","volume":"33","author":"Reich","year":"1996","journal-title":"SIAM Journal on Numerical Analysis"},{"key":"2023030906302096500_","doi-asserted-by":"crossref","first-page":"603","DOI":"10.1093\/biomet\/88.3.603","article-title":"On inference for partially observed nonlinear diffusion models using the Metropolis\u2013Hastings algorithm","volume":"88","author":"Roberts","year":"2001","journal-title":"Biometrika"},{"key":"2023030906302096500_","volume-title":"Free Energy Computations: A Mathematical Perspective","author":"Rousset","year":"2010"},{"key":"2023030906302096500_","first-page":"4423","volume-title":"Black-box variational inference for stochastic differential equations","author":"Ryder","year":"2018"},{"key":"2023030906302096500_","doi-asserted-by":"crossref","first-page":"531","DOI":"10.1007\/978-3-540-71297-8_23","volume-title":"Handbook of financial time series","author":"S\u00f8rensen","year":"2009"},{"key":"2023030906302096500_","doi-asserted-by":"crossref","first-page":"339","DOI":"10.1007\/s11222-012-9373-1","article-title":"Split Hamiltonian Monte Carlo","volume":"24","author":"Shahbaba","year":"2014","journal-title":"Statistics and Computing"},{"key":"2023030906302096500_","doi-asserted-by":"crossref","first-page":"653","DOI":"10.1093\/biomet\/84.3.653","article-title":"Likelihood analysis of non-Gaussian measurement time series","volume":"84","author":"Shephard","year":"1997","journal-title":"Biometrika"},{"key":"2023030906302096500_","volume-title":"Rank-normalization, folding, and localization: An improved R^ for assessing convergence of MCMC","author":"Vehtari","year":"2019"},{"key":"2023030906302096500_","doi-asserted-by":"crossref","first-page":"98","DOI":"10.1103\/PhysRev.159.98","article-title":"Computer \u2018experiment\u2019 on classical fluids. i. thermodynamical properties of Lennard\u2013Jones molecules","volume":"159","author":"Verlet","year":"1967","journal-title":"Physical Review"},{"key":"2023030906302096500_","doi-asserted-by":"crossref","first-page":"2609","DOI":"10.1002\/cpa.21783","article-title":"Monte Carlo on manifolds: sampling densities and integrating functions","volume":"71","author":"Zappa","year":"2018","journal-title":"Communications on Pure and Applied Mathematics"}],"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.12497","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1111\/rssb.12497","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/academic.oup.com\/jrsssb\/article-pdf\/84\/4\/1229\/49463308\/jrsssb_84_4_1229.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jrsssb\/article-pdf\/84\/4\/1229\/49463308\/jrsssb_84_4_1229.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T05:51:27Z","timestamp":1700459487000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jrsssb\/article\/84\/4\/1229\/7073285"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,4,19]]},"references-count":59,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2022,4,19]]},"published-print":{"date-parts":[[2022,9,1]]}},"URL":"https:\/\/doi.org\/10.1111\/rssb.12497","relation":{},"ISSN":["1369-7412","1467-9868"],"issn-type":[{"value":"1369-7412","type":"print"},{"value":"1467-9868","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2022,9]]},"published":{"date-parts":[[2022,4,19]]}}}