Batch Bayesian optimization
Author(s)Hunt, Nathan(Nathan R.)
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science.
David K. Gifford.
MetadataShow full item record
Bayesian optimization is a useful technique for maximizing expensive, unknown functions that employs an acquisition function to determine what unseen input point to query next. In many real-world applications, batches of input points can be queried simultaneously for only a small marginal cost compared to querying a single point. Most classical acquisition functions cannot be used for batch acquisition, and thus batch acquisition strategies are required. Several such strategies have been developed in the past decade. We review and compare batch acquisition strategies in a variety of settings to assist practitioners in selecting appropriate batch acquisition functions and facilitate further research in this area.
Thesis: S.M., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, February, 2020Cataloged from PDF version of thesis. "Pages contain copy print steak marks"--Disclaimer page.Includes bibliographical references (pages 73-77).
DepartmentMassachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Massachusetts Institute of Technology
Electrical Engineering and Computer Science.