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 …

Bayesian formulations of deep learning have been shown to have compelling theoretical
properties and offer practical functional benefits, such as improved predictive uncertainty …

Deep ensembles have recently gained popularity in the deep learning community for their
conceptual simplicity and efficiency. However, maintaining functional diversity between …

In the current landscape of deep learning research, there is a predominant emphasis on
achieving high predictive accuracy in supervised tasks involving large image and language …

Neural network (NN) potentials promise highly accurate molecular dynamics (MD)
simulations within the computational complexity of classical MD force fields. However, when …

In the current landscape of deep learning research, there is a predominant emphasis on
achieving high predictive accuracy in supervised tasks involving large image and language …

Bayesian neural networks that incorporate data augmentation implicitly use a “randomly
perturbed log-likelihood [which] does not have a clean interpretation as a valid likelihood …

Ensembles of deep neural networks have achieved great success recently, but they do not
offer a proper Bayesian justification. Moreover, while they allow for averaging of predictions …

Bayesian neural networks have shown great promise in many applications where calibrated
uncertainty estimates are crucial and can often also lead to a higher predictive performance …

The linearized-Laplace approximation (LLA) has been shown to be effective and efficient in
constructing Bayesian neural networks. It is theoretically compelling since it can be seen as …