Data-driven Multistage Distributionally Robust Optimization with Nested Distance: Time Consistency and Tractable Dynamic Reformulations
We study multistage distributionally robust optimization in which the uncertainty set consists of stochastic processes that are close to a scenario tree in the nested distance (Pflug and Pichler (2012)). Compared to other choices such as Wasserstein distance between stochastic processes, the nested distance accounts for information evolution, making it hedge against a plausible family … Read more