Deep Ensembles from a Bayesian Perspective
arXiv:2105.13283
Abstract
Deep ensembles can be considered as the current state-of-the-art for uncertainty quantification in deep learning. While the approach was originally proposed as a non-Bayesian technique, arguments supporting its Bayesian footing have been put forward as well. We show that deep ensembles can be viewed as an approximate Bayesian method by specifying the corresponding assumptions. Our findings lead to an improved approximation which results in an enlarged epistemic part of the uncertainty. Numerical examples suggest that the improved approximation can lead to more reliable uncertainties. Analytical derivations ensure easy calculation of results.
References in corpus (14)
- A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challenges
- Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift
- Hands-on Bayesian Neural Networks -- a Tutorial for Deep Learning Users
- Deep Ensembles: A Loss Landscape Perspective
- Bayesian Deep Learning and a Probabilistic Perspective of Generalization
- Testing Deep Neural Networks
- A Simple Baseline for Bayesian Uncertainty in Deep Learning
- Deeply Uncertain: Comparing Methods of Uncertainty Quantification in Deep Learning Algorithms
- Quality of Uncertainty Quantification for Bayesian Neural Network Inference
- Explainability Techniques for Graph Convolutional Networks
- Hyperparameter Ensembles for Robustness and Uncertainty Quantification
- Bayesian Deep Ensembles via the Neural Tangent Kernel
- The Relevance of Bayesian Layer Positioning to Model Uncertainty in Deep Bayesian Active Learning
- On Last-Layer Algorithms for Classification: Decoupling Representation from Uncertainty Estimation