# Priors in Bayesian Deep Learning: A Review

**Authors:** Vincent Fortuin  
**arXiv:** [2105.06868](https://arxiv.org/abs/2105.06868)  
**Date:** 2021-05-14  
**Summary page:** https://www.summarizepaper.com/en/arxiv-id/2105.06868v3/

## Key points

- The paper emphasizes the significance of prior choices in Bayesian deep learning models
- Recent models have often used vague priors like standard Gaussians
- The review provides an overview of different priors proposed for (deep) Gaussian processes, variational autoencoders, and Bayesian neural networks
- Various methods for learning priors from data are discussed in detail
- The review aims to inspire practitioners to think more carefully about their model's prior choices
- The paper serves as a valuable resource for researchers and practitioners seeking guidance on selecting appropriate priors for their Bayesian deep learning models
- Prior choices play a crucial role in Bayesian deep learning and practitioners should consider more informed and tailored prior specifications

## Summary

The paper titled "Priors in Bayesian Deep Learning: A Review" by Vincent Fortuin emphasizes the significance of prior choices in Bayesian deep learning models. While the choice of prior is a critical aspect of the Bayesian inference workflow, recent models have often resorted to vague priors like standard Gaussians. This review aims to highlight the importance of thoughtful prior specification and provides an overview of different priors proposed for (deep) Gaussian processes, variational autoencoders, and Bayesian neural networks. The authors discuss various methods for learning priors from data and present them in detail. By exploring different approaches to prior specification, this review intends to inspire practitioners in Bayesian deep learning to think more carefully about their model's prior choices. The paper serves as a valuable resource for researchers and practitioners seeking guidance on selecting appropriate priors for their Bayesian deep learning models. Overall, this comprehensive review sheds light on the crucial role that prior choices play in Bayesian deep learning and encourages practitioners to consider more informed and tailored prior specifications for their models.