Journal
INTERNATIONAL STATISTICAL REVIEW
Volume 90, Issue 3, Pages 563-591Publisher
WILEY
DOI: 10.1111/insr.12502
Keywords
Bayesian deep learning; Bayesian learning; deep learning; priors
Categories
Funding
- Swiss Data Science Center
Ask authors/readers for more resources
The choice of prior is crucial for Bayesian deep learning models, and different models require different types of priors. Learners should pay more attention to prior specifications and gain inspiration from them.
While the choice of prior is one of the most critical parts of the Bayesian inference workflow, recent Bayesian deep learning models have often fallen back on vague priors, such as standard Gaussians. In this review, we highlight the importance of prior choices for Bayesian deep learning and present an overview of different priors that have been proposed for (deep) Gaussian processes, variational autoencoders and Bayesian neural networks. We also outline different methods of learning priors for these models from data. We hope to motivate practitioners in Bayesian deep learning to think more carefully about the prior specification for their models and to provide them with some inspiration in this regard.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available