Reviews: Budgeted stream-based active learning via adaptive submodular maximization

Pros: The presentation is mostly clear. The paper shows that one can apply the proposed streaming algorithm, without changing the commonly used objective functions used in pool-based active learning setting. Proofs are sound, and experimental results show that the proposed algorithms work reasonably well in comparison with the pool-based setting. Cons: The stream-based adaptive sensor placement application does not appear convincing to me. Is the condition range(\pi) \subseteq V \setminus B in Def 3.1 necessary? Policy-adaptive submodularity is used for providng a lower bound on the expected gain of a policy on a random sequence of data points (Lemma B.7).