important problem setting of active learning for combinatorial pool-based FDR control - a problem of tantamount

We now dive into these ideas more carefully and address specific comments by the reviewers. Thank you for the encouraging review. The proof relies heavily on the sampling scheme and the choice of estimators. Thank you for your comments. This also relates to your concerns in points 3 and 4. Bounds in statistical learning theory based on VC (local) dimensions They have received less attention in the bandit and active learning literature.