On the Effects of Quantisation on Model Uncertainty in Bayesian Neural Networks

Abstract

Bayesian neural networks (BNNs) are making significant progress in many research areas where decision-making needs to be accompanied by uncertainty estimation. Being able to quantify uncertainty while making decisions is essential for understanding when the model is over-/under-confident, and hence BNNs are attracting interest in safety-critical applications, such as autonomous driving, healthcare, and robotics. Nevertheless, BNNs have not been as widely used in industrial practice, mainly because of their increased memory and compute costs. In this work, we investigate quantisation of BNNs by compressing 32-bit floating-point weights and activations to their integer counterparts, that has already been successful in reducing the compute demand in standard pointwise neural networks. We study three types of quantised BNNs, we evaluate them under a wide range of different settings, and we empirically demonstrate that a uniform quantisation scheme applied to BNNs does not substantially decrease their quality of uncertainty estimation.

arXiv commentAccepted at UAI2021. Code at: https://github.com/martinferianc/quantised-bayesian-nets

References in corpus (11)

• Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation
• On Calibration of Modern Neural Networks
• Weight Uncertainty in Neural Networks
• Quantizing deep convolutional networks for efficient inference: A whitepaper
• Stochastic Gradient Hamiltonian Monte Carlo
• A Survey of FPGA-Based Neural Network Accelerator
• VIBNN: Hardware Acceleration of Bayesian Neural Networks
• Bayesian Bits: Unifying Quantization and Pruning
• Dropout as a Bayesian Approximation: Appendix
• Variational Gaussian Dropout is not Bayesian
• Sampling-Free Learning of Bayesian Quantized Neural Networks