However, such methods are usually sensitive to environmental dynamics-irrelevant information, e.g., white-noise. To handle such dynamics-irrelevant information, we propose a Dynamic Bottleneck (DB) model, which attains a dynamics-relevant representation based on the information-bottleneck principle.

However, most systems of practical interest are non-linear, requiring more complex models. Many approximate inference methods have been developed for non-linear dynamical systems: Deterministic methods approximate the filtering and smoothing distributions e.g. by using a Taylor series

We first introduce Equivari-ant Stein V ariational Gradient Descent algorithm - an equivariant sampling method based on Stein's identity for sampling from densities with symmetries.

It is now employed to make critical decisions that affect our lives, cultures, and rights, e.g., screening job applicants, and informing bail & parole decisions.

How to achieve such spatial adaptation in a principled manner has been an open problem in both traditional model-based and modern learning-based approaches toward SISR. In this paper, we propose a new adaptive weighted loss for SISR to train deep networks focusing on challenging situations such as textured and edge pixels with high uncertainty.