Popular algorithms suchasUCB[4,5]andThompson sampling [3,34]typically explorethearms sufficiently and as more evidence is gathered, converge to the optimal arm.

Imbalanced learning(IL),i.e.,learning unbiased models from class-imbalanced data, is a challenging problem.

To address this, we propose a new probabilistic framework for DG where the goal is to learn predictors that perform wellwith highprobability.

Our framework enables the development of the first fully data-driven solutions to active touch on top of learned models for object understanding.