Here W is a d m matrix whose columns are components for tensorT.

We illustrate our findings with simple and realworldout-of-distribution(OOD)generalizationexperiments.

To obtain useful guarantees, it is necessary to study data models that encode structure reflective of settings of interest.

Checklists are simple decision aids that are often used to promote safety and reliability in clinical applications. In this paper, we present a method to learn checklists for clinical decision support. We represent predictive checklists as discrete linear classifiers with binary features and unit weights.