Given time series data, how can we answer questions like "what will happen in the future?" and "how did we get here?"

It has inspired various applications in molecular property prediction and drug design.

Tweedie's formula, we show that we can perform gradient steps to sequentially optimize these objectives.

Most applications of machine learning to classification assume a closed set of balanced classes.

BACON allows computational resources to be focused on simulations that provide the most value in terms of reducing epistemic uncertainty.