Model Architecture Adaption for Bayesian Neural Networks
Wang, Duo, Zhao, Yiren, Shumailov, Ilia, Mullins, Robert
–arXiv.org Artificial Intelligence
Bayesian Neural Networks (BNNs) offer a mathematically grounded framework to quantify the uncertainty of model predictions but come with a prohibitive computation cost for both training and inference. In this work, we show a novel network architecture search (NAS) that optimizes BNNs for both accuracy and uncertainty while having a reduced inference latency. Different from canonical NAS that optimizes solely for in-distribution likelihood, the proposed scheme searches for the uncertainty performance using both in- and out-of-distribution data. Our method is able to search for the correct placement of Bayesian layer(s) in a network. In our experiments, the searched models show comparable uncertainty quantification ability and accuracy compared to the state-of-the-art (deep ensemble). In addition, the searched models use only a fraction of the runtime compared to many popular BNN baselines, reducing the inference runtime cost by $2.98 \times$ and $2.92 \times$ respectively on the CIFAR10 dataset when compared to MCDropout and deep ensemble.
arXiv.org Artificial Intelligence
Feb-9-2022
- Country:
- Europe > United Kingdom > England > Cambridgeshire > Cambridge (0.14)
- Genre:
- Research Report > New Finding (0.34)
- Industry:
- Health & Medicine (0.47)