We apply gradient strategy methods, developed in the literature on robust optimization, approachability and calibration, to develop new bounds for option prices. While this literature focuses on asymptotic performance, we provide a financial interpretation of these methods by demonstrating how...

We study a novel mechanism design model in which agents each arrive sequentially and choose one action from a set of actions with unknown rewards. The information revealed by the principal affects the incentives of the agents to explore and generate new information. We characterize the optimal...