While the choice of prior is one of the most critical parts of the Bayesian inference workflow,
recent Bayesian deep learning models have often fallen back on vague priors, such as …

We advocate an optimization-centric view of Bayesian inference. Our inspiration is the
representation of Bayes' rule as infinite-dimensional optimization (Csisz´ r, 1975; Donsker …

Neural networks have achieved remarkable performance across various problem domains,
but their widespread applicability is hindered by inherent limitations such as overconfidence …

We introduce a probability distribution, combined with an efficient sampling algorithm, for
weights and biases of fully-connected neural networks. In a supervised learning context, no …

The Bayesian treatment of neural networks dictates that a prior distribution is specified over
their weight and bias parameters. This poses a challenge because modern neural networks …

Predicting properties of proteins is of interest for basic biological understanding and protein
engineering alike. Increasingly, machine learning (ML) approaches are being used for this …

Conventional Bayesian Neural Networks (BNNs) cannot leverage unlabelled data to
improve their predictions. To overcome this limitation, we introduce Self-Supervised …

Given any deep fully connected neural network, initialized with random Gaussian
parameters, we bound from above the quadratic Wasserstein distance between its output …

We study the extent to which wide neural networks may be approximated by Gaussian
processes, when initialized with random weights. It is a well-established fact that as the …

It is challenging to guide neural network (NN) learning with prior knowledge. In contrast,
many known properties, such as spatial smoothness or seasonality, are straightforward to …