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 …

The posterior over Bayesian neural network (BNN) parameters is extremely high-
dimensional and non-convex. For computational reasons, researchers approximate this …

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

Prior Knowledge Elicitation: The Past, Present, and Future Page 1 Bayesian Analysis (2024)
19, Number 4, pp. 1129–1161 Prior Knowledge Elicitation: The Past, Present, and Future ∗ …

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 …

We develop a new Bayesian framework based on deep neural networks to be able to
extrapolate in space-time using historical data and to quantify uncertainties arising from both …

Bayesian neural networks (BNNs) have recently gained popularity due to their ability to
quantify model uncertainty. However, specifying a prior for BNNs that captures relevant …

Bayesian optimization (BO) has become a popular strategy for global optimization of
expensive real-world functions. Contrary to a common expectation that BO is suited to …

In this paper, three state-of-the-art deep learning uncertainty quantification (UQ) methods–
Flipout probabilistic convolutional neural network (CNN), deep ensemble probabilistic CNN …

We propose a novel modular inference approach combining two different generative models—
generative adversarial networks (GAN) and normalizing flows—to approximate the posterior …