Our approach can be used with any decision-theoretic acquisition function and is readily compatible with trust region methods like TuRBO.

Human languages support both semantic categorization and local pragmatic interactions that require context-sensitive reasoning about meaning.

This thresholding can further exacerbate the aforementioned degeneracy.

Here, we integrate these two approaches by trading off utility, informativeness, and complexity in EC.

We consider the problem of estimating states ( e.g., position and velocity) and physical parameters ( e.g., friction, elasticity) from a sequence of observations

Deep neural networks are known to be vulnerable to small adversarial perturbations in test data. To defend against adversarial attacks, probabilistic classifiers have been proposed as an alternative to deterministic ones. However, literature has conflicting findings on the effectiveness of probabilistic classifiers in comparison to deterministic ones.