While it possesses many desirable structural properties, the estimation of high-dimensional MI from samples suffers from the curse of dimensionality.

The performance of the proposed algorithm is evaluated on a wide variety of machine learning tasks.

While Bayesian neural networks (BNNs) hold the promise of being flexible, well-calibrated statistical models, inference often requires approximations whose consequences are poorly understood.

We revisit the work of Etheve et al.

POMGs--in which sample-efficient learning is tractable.