Open Access
February 2024 Emerging Directions in Bayesian Computation
Steven Winter, Trevor Campbell, Lizhen Lin, Sanvesh Srivastava, David B. Dunson
Author Affiliations +
Statist. Sci. 39(1): 62-89 (February 2024). DOI: 10.1214/23-STS919


Bayesian models are powerful tools for studying complex data, allowing the analyst to encode rich hierarchical dependencies and leverage prior information. Most importantly, they facilitate a complete characterization of uncertainty through the posterior distribution. Practical posterior computation is commonly performed via MCMC, which can be computationally infeasible for high-dimensional models with many observations. In this article, we discuss the potential to improve posterior computation using ideas from machine learning. Concrete directions are explored in vignettes on normalizing flows, statistical properties of variational approximations, Bayesian coresets and distributed Bayesian inference.

Funding Statement

This research was partially supported by the Lifeplan project funded by the European Research Council under the European Union’s Horizon 2020 research and innovation programme (Grant Agreement No. 856506). Additional funding came from the United States Office of Naval Research (N000142112510) and National Institutes of Health (R01-ES028804, R01-ES035625).


T. Campbell, L. Lin and S. Srivastava contributed equally.


Download Citation

Steven Winter. Trevor Campbell. Lizhen Lin. Sanvesh Srivastava. David B. Dunson. "Emerging Directions in Bayesian Computation." Statist. Sci. 39 (1) 62 - 89, February 2024.


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

MathSciNet: MR4718527
Digital Object Identifier: 10.1214/23-STS919

Keywords: coresets , Federated learning , machine learning , normalizing flows , posterior computation , variational Bayes

Rights: Copyright © 2024 Institute of Mathematical Statistics

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