February 2024 Modern Bayesian Experimental Design
Tom Rainforth, Adam Foster, Desi R. Ivanova, Freddie Bickford Smith
Author Affiliations +
Statist. Sci. 39(1): 100-114 (February 2024). DOI: 10.1214/23-STS915


Bayesian experimental design (BED) provides a powerful and general framework for optimizing the design of experiments. However, its deployment often poses substantial computational challenges that can undermine its practical use. In this review, we outline how recent advances have transformed our ability to overcome these challenges and thus utilize BED effectively, before discussing some areas for future development in the field.

Funding Statement

Desi R. Ivanova was supported by the EPSRC Centre for Doctoral Training in Modern Statistics and Statistical Machine Learning (EP/S023151/1). Freddie Bickford Smith was supported by the EPSRC Centre for Doctoral Training in Autonomous Intelligent Machines and Systems (EP/S024050/1).


We would like to thank Dennis Prangle and Christian Robert for inviting us to write this paper and their helpful feedback during the review process. We would also like to thank the additional anonymous reviewer for their useful suggestions.


Download Citation

Tom Rainforth. Adam Foster. Desi R. Ivanova. Freddie Bickford Smith. "Modern Bayesian Experimental Design." Statist. Sci. 39 (1) 100 - 114, February 2024. https://doi.org/10.1214/23-STS915


Published: February 2024
First available in Project Euclid: 18 February 2024

MathSciNet: MR4718529
Digital Object Identifier: 10.1214/23-STS915

Keywords: Active learning , Bayesian adaptive design , Bayesian optimal design , information maximization

Rights: This research was funded, in whole or in part, by [EPSRC, EP/SO23151/1]. A CC BY 4.0 license is applied to this article arising from this submission, in accordance with the grant’s open access conditions.


This article is only available to subscribers.
It is not available for individual sale.

Vol.39 • No. 1 • February 2024
Back to Top