BAYESIAN SEQUENTIAL OPTIMAL EXPERIMENTAL DESIGN FOR INVERSE PROBLEMS USING DEEP REINFORCEMENT LEARNING

Loading...

View/Download File

Anderson_umn_0130E_23160.pdf (1.88 MB)

Persistent link to this item

https://hdl.handle.net/11299/241402

Statistics

View Statistics

Journal Title

Journal ISSN

Volume Title

Title

BAYESIAN SEQUENTIAL OPTIMAL EXPERIMENTAL DESIGN FOR INVERSE PROBLEMS USING DEEP REINFORCEMENT LEARNING

Authors

Anderson, Loren

Published Date

2022-04

Publisher

Type

Thesis or Dissertation

Abstract

We perform a comprehensive study on Bayesian sequential optimal experimental design techniquesapplied to inverse problems. We transform the Bayesian sequential optimal experimental design problem into a reinforcement learning problem to gauge the power of recent deep reinforcement learning algorithms compared to other baseline algorithms. Using KL-divergence as a measure of information gain, we construct objectives to maximize information gain for batch design, greedy design, black-box Bayesian optimization, multi-armed bandit optimization, dynamic programming, approximate dynamic programming, and reinforcement learning. This work showcases novel comparisons between the aforementioned methods and a new application of off-the-shelf reinforcement learning algorithms to Bayesian sequential optimal experimental design for inverse problems in differential equation models.

Keywords

Bayesian Experimental Design

Deep Reinforcement Learning

Information Gain

Inverse Problems

Optimal Experimental Design

Sequential Experimental Design

Description

University of Minnesota Ph.D. dissertation. 2022. Major: Mathematics. Advisor: Fadil Santosa. 1 computer file (PDF); 113 pages.

Related to

Replaces

License

Collections

Dissertations

Series/Report Number

Funding information

Isbn identifier

Doi identifier

Previously Published Citation

Suggested citation

Anderson, Loren. (2022). BAYESIAN SEQUENTIAL OPTIMAL EXPERIMENTAL DESIGN FOR INVERSE PROBLEMS USING DEEP REINFORCEMENT LEARNING. Retrieved from the University Digital Conservancy, https://hdl.handle.net/11299/241402.

Content distributed via the University Digital Conservancy may be subject to additional license and use restrictions applied by the depositor. By using these files, users agree to the Terms of Use. Materials in the UDC may contain content that is disturbing and/or harmful. For more information, please see our statement on harmful content in digital repositories.