Bayesian statistics is an approach to data analysis based on Bayes' theorem, where
available knowledge about parameters in a statistical model is updated with the information …

Uncertainty quantification (UQ) methods play a pivotal role in reducing the impact of
uncertainties during both optimization and decision making processes. They have been …

Neural networks (NNs) are currently changing the computational paradigm on how to
combine data with mathematical laws in physics and engineering in a profound way …

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

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

Deep learning bears promise for drug discovery, including advanced image analysis,
prediction of molecular structure and function, and automated generation of innovative …

Deep ensembles have been empirically shown to be a promising approach for improving
accuracy, uncertainty and out-of-distribution robustness of deep learning models. While …

Algorithmic transparency entails exposing system properties to various stakeholders for
purposes that include understanding, improving, and contesting predictions. Until now, most …

Abstract We propose SWA-Gaussian (SWAG), a simple, scalable, and general purpose
approach for uncertainty representation and calibration in deep learning. Stochastic Weight …

Sparse modeling for signal processing and machine learning, in general, has been at the
focus of scientific research for over two decades. Among others, supervised sparsity-aware …