Show simple item record

dc.contributor.authorIzzatullah, Muhammad
dc.contributor.authorBaptista, Ricardo
dc.contributor.authorMackey, Lester
dc.contributor.authorMarzouk, Youssef
dc.contributor.authorPeter, Daniel
dc.date.accessioned2021-02-22T10:45:22Z
dc.date.available2021-02-22T10:45:22Z
dc.date.issued2020-09-25
dc.identifier.citationIzzatullah, M., Baptista, R., Mackey, L., Marzouk, Y., & Peter, D. (2020). Bayesian seismic inversion: Measuring Langevin MCMC sample quality with kernels. SEG Technical Program Expanded Abstracts 2020. doi:10.1190/segam2020-3422419.1
dc.identifier.doi10.1190/segam2020-3422419.1
dc.identifier.urihttp://hdl.handle.net/10754/667572
dc.description.abstractThe Bayesian framework is commonly used to quantify uncertainty in seismic inversion. To perform Bayesian inference, Markov chain Monte Carlo (MCMC) algorithms are regarded as the gold standard technique for sampling from the posterior probability distribution. Consistent MCMC methods have trouble for complex, high-dimensional models, and most methods scale poorly to large datasets, such as those arising in seismic inversion. As an alternative, approximate MCMC methods based on unadjusted Langevin dynamics offer scalability and more rapid sampling at the cost of biased inference. However, when assessing the quality of approximate MCMC samples for characterizing the posterior distribution, most diagnostics fail to account for these biases. In this work, we introduce the kernel Stein discrepancy (KSD) as a diagnostic tool to determine the convergence of MCMC samples for Bayesian seismic inversion. We demonstrate the use of the KSD for measuring sample quality and selecting the optimal Langevin MCMC algorithm for two Gaussian Bayesian inference problems.
dc.description.sponsorshipThis publication is based on work supported by King Abdul-lah University of Science and Technology (KAUST) and the Seismic Modeling and Inversion (SMI) group at KAUST.
dc.publisherSociety of Exploration Geophysicists
dc.relation.urlhttps://library.seg.org/doi/10.1190/segam2020-3422419.1
dc.rightsArchived with thanks to Society of Exploration Geophysicists
dc.titleBayesian seismic inversion: Measuring Langevin MCMC sample quality with kernels
dc.typeConference Paper
dc.contributor.departmentEarth Science and Engineering Program
dc.contributor.departmentPhysical Science and Engineering (PSE) Division
dc.contributor.departmentExtreme Computing Research Center
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
dc.conference.nameSEG International Exposition and 90th Annual Meeting
dc.eprint.versionPre-print
dc.contributor.institutionMassachusetts Institute of Technology
dc.contributor.institutionMicrosoft Research New England
kaust.personIzzatullah, Muhammad
kaust.personPeter, Daniel


This item appears in the following Collection(s)

Show simple item record