The University of Arizona: Bayesian Optimal Experimental Design Via Exact Variational Approximations
Bayesian optimal experimental design (BOED) is a framework that uses statistical models and decision making under uncertainty to optimize the cost and performance of a scientific experiment.
Mutual information (MI) is a commonly adopted utility function in BOED. While theoretically appealing, MI evaluation poses a significant computational burden for most real world applications, where the data generating distribution is intractable, but sampling from it is possible. A common approach is Variational Approximations where the intractable distribution is approximated by a more computationally friendly approximation. In this talk, we will introduce a new variational method to approximating MI and explore its use in some common examples.
Series: Program in Applied Mathematics Brown Bag Seminar
Hybrid: Math 402/Online
Presenter: Caleb Dahlke, Program in Applied Mathematics, University of Arizona
Place: Math, 402 and Zoom: https://arizona.zoom.us/j/82075792519 Password: 150721
- Audience: Adult
- Genre: Mathematics
- Type: Hybrid, Presentation