Papers¶
This page highlights some of the key papers that we will go over during the working group. I have organized the sections into topics and each section will have the appropriate literature. I will keep the papers that we will go in detail near the top and any supporting papers will go at the bottom.
!> Warning: This is not the final list. This is merely a guide that we will pivot off of.
Bayesian¶
- The prior can generally only be understood in the context of the likelihood - Gelman et. al. (2017) - arxiv | blog
Introduction to Bayesian Deep Learning¶
- Practical Deep Learning with Bayesian Principles - Warner & Neal (1997) -arxiv
- Towards Bayesian Deep Learning: A Survey - Wang et. al. (2016)
Approximately Bayesian¶
- Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning - Gal & Ghahramani - Paper | Code | Tutorial | Blog
Computer Vision¶
- What Uncertainties do We Need for BDL for CV - Kendall & Gal (2017) - arxiv |
- A Comprehensive guide to Bayesian Convolutional NeuralNetwork with Variational Inference - Shridhar et. al. (2018) - arxiv | code (PyTorch)
SOTA¶
Bayesian Deep Learning and a Probabilistic Perspective of Generalization - AGW & Pavel Izmailov - PDF
The Case for Bayesian Deep Learning - AGW - ARXIV
Cyclical Stochastic Gradient MCMC for Bayesian Deep Learning - Zhang et al - arxiv | Code
- Stochastic Weighted Averaging - SWA | Paper
- Stochastic Weighted Averaging - SWAG | Paper
- Stochastic Weighted Averaging - Multi-SWAG