Stabilising priors for robust Bayesian deep learning
This addresses the problem of unstable training in Bayesian deep learning for researchers and practitioners, representing an incremental improvement with a novel method for a known bottleneck.
The paper tackled the brittleness and training difficulties of Bayesian neural networks (BNNs) in deep architectures and high weight variance scenarios by proposing self-stabilising priors, which improved convergence and robustness, enabling training of deeper networks and in noisier settings.
Bayesian neural networks (BNNs) have developed into useful tools for probabilistic modelling due to recent advances in variational inference enabling large scale BNNs. However, BNNs remain brittle and hard to train, especially: (1) when using deep architectures consisting of many hidden layers and (2) in situations with large weight variances. We use signal propagation theory to quantify these challenges and propose self-stabilising priors. This is achieved by a reformulation of the ELBO to allow the prior to influence network signal propagation. Then, we develop a stabilising prior, where the distributional parameters of the prior are adjusted before each forward pass to ensure stability of the propagating signal. This stabilised signal propagation leads to improved convergence and robustness making it possible to train deeper networks and in more noisy settings.