In 1996, Accountability in a Computerized Society [95] issued a clarion call concerning the
erosion of accountability in society due to the ubiquitous delegation of consequential …

Bayesian approaches for learning deep neural networks (BNN) have been received much
attention and successfully applied to various applications. Particularly, BNNs have the merit …

Trade-offs between accuracy and efficiency pervade law, public health, and other non-
computing domains, which have developed policies to guide how to balance the two in …

Variational inference is a powerful paradigm for approximate Bayesian inference with a
number of appealing properties, including support for model learning and data subsampling …

Bayesian inference provides a principled framework for learning from complex data and
reasoning under uncertainty. It has been widely applied in machine learning tasks such as …

Bayesian neural networks (BNNs) offer uncertainty quantification but come with the
downside of substantially increased training and inference costs. Sparse BNNs have been …

Uncertainty estimation is a key issue when considering the application of deep neural
network methods in science and engineering. In this work, we introduce a novel algorithm …

Bayesian deep learning counts on the quality of posterior distribution estimation. However,
the posterior of deep neural networks is highly multi-modal in nature, with local modes …

In sampling tasks, it is common for target distributions to be known up to a normalising
constant. However, in many situations, evaluating even the unnormalised distribution can be …

The posterior probability density distribution of updating parameters within the Bayesian
model updating framework is relatively complex, and effective sampling techniques are …