Wasserstein robust combinatorial optimization problems

Abstract: This paper discusses a class of combinatorial optimization problems with uncertain costs in the objective function. It is assumed that a sample of the cost realizations is available, which defines an empirical probability distribution for the random cost vector. A Wasserstein ball, centered at the empirical distribution, is used to define an ambiguity set of probability distributions. A solution minimizing the Conditional Value at Risk for a worst probability distribution in the Wasserstein ball is computed. The complexity of the problem is investigated. Exact and approximate solution methods for various support sets are proposed. Some known results for the Wasserstein robust shortest path problem are generalized and refined.