First-order Conditions for Optimization in the Wasserstein Space

We study first-order optimality conditions for constrained optimization in the Wasserstein space, whereby one seeks to minimize a real-valued function over the space of probability measures endowed with the Wasserstein distance. Our analysis combines recent insights on the geometry and the differential structure of the Wasserstein space with more classical calculus of variations. Perhaps surprisingly, we show that simple rationales such as “setting the derivative to zero” and “gradients are aligned at optimality” carry over to the Wasserstein space. We deploy our tools to study and solve optimization problems in the setting of distributionally robust optimization and statistical inference. The generality of our methodology allows us to naturally deal with functionals, such as the mean-variance, the Kullback-Leibler divergence, and the Wasserstein distance, which are traditionally difficult to study in a unified framework.