Stochastic Monotone Submodular Maximization with Queries

We study a stochastic variant of monotone submodular maximization problem as follows. We are given a monotone submodular function as an objective function and a feasible domain defined on a finite set, and our goal is to find a feasible solution that maximizes the objective function. A special part of the problem is that each element in the finite set has a random hidden state, active or inactive, only the active elements contribute to the objective value, and we can conduct a query to an element to reveal its hidden state. The goal is to obtain a feasible solution having a large objective value by conducting a small number of queries. This is the first attempt to consider nonlinear objective functions in such a stochastic model. We prove that the problem admits a good query strategy if the feasible domain has a uniform exchange property. This result generalizes Blum et al.'s result on the unweighted matching problem and Behnezhad and Reyhani's result on the weighted matching problem in both objective function and feasible domain.