Show simple item record

dc.contributor.advisorYoussef Marzouk.en_US
dc.contributor.authorLi, Fengyi,S.M.Massachusetts Institute of Technology.en_US
dc.contributor.otherMassachusetts Institute of Technology. Department of Aeronautics and Astronautics.en_US
dc.date.accessioned2019-10-04T21:30:46Z
dc.date.available2019-10-04T21:30:46Z
dc.date.copyright2019en_US
dc.date.issued2019en_US
dc.identifier.urihttps://hdl.handle.net/1721.1/122376
dc.descriptionThis electronic version was submitted by the student author. The certified thesis is available in the Institute Archives and Special Collections.en_US
dc.descriptionThesis: S.M., Massachusetts Institute of Technology, Department of Aeronautics and Astronautics, 2019en_US
dc.descriptionCataloged from student-submitted PDF version of thesis.en_US
dc.descriptionIncludes bibliographical references (pages 83-87).en_US
dc.description.abstractOptimal experimental design plays an important role in science and engineering. In many situations, we have many observations but only few of them can be selected due to limited resources. We then need to decide which ones to select based on our goal. In this thesis, we study the Bayesian linear Gaussian model with a large number of observations, and propose several algorithms for solving the combinatorial problem of observation selection/optimal experimental design in a goal-oriented setting. Here, the quantity of interest (QoI) is not the model parameters, but some (vector-valued) function of the parameters. We wish to select a subset of the candidate observations that is most informative for this QoI, in the sense of reducing its uncertainty. More precisely, we seek to maximize the mutual information between the selected observations and the QoI. Finding the true optimum is NP-hard, and in this setting, the mutual information objective is in general not submodular. We thus introduce several algorithms that approximate the optimal solution, including a greedy approach, a minorize-maximize approach employing modular bounds, and certain score-based heuristics. We compare the computational cost these algorithms, and demonstrate their performance on a synthetic data set and a real data set from a climate model.en_US
dc.description.sponsorshipSupport from Department of Energyen_US
dc.description.statementofresponsibilityby Fengyi Li.en_US
dc.format.extent87 pagesen_US
dc.language.isoengen_US
dc.publisherMassachusetts Institute of Technologyen_US
dc.rightsMIT theses are protected by copyright. They may be viewed, downloaded, or printed from this source but further reproduction or distribution in any format is prohibited without written permission.en_US
dc.rights.urihttp://dspace.mit.edu/handle/1721.1/7582en_US
dc.subjectAeronautics and Astronautics.en_US
dc.titleA combinatorial approach to goal-oriented optimal Bayesian experimental designen_US
dc.typeThesisen_US
dc.description.degreeS.M.en_US
dc.contributor.departmentMassachusetts Institute of Technology. Department of Aeronautics and Astronauticsen_US
dc.identifier.oclc1119730930en_US
dc.description.collectionS.M. Massachusetts Institute of Technology, Department of Aeronautics and Astronauticsen_US
dspace.imported2019-10-04T21:30:44Zen_US
mit.thesis.degreeMasteren_US
mit.thesis.departmentAeroen_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record