Regularization for Wasserstein Distributionally Robust Optimization

Understand

Optimal transport has recently proved to be a useful tool in various machine learning applications needing comparisons of probability measures.

• Among these, applications of distributionally robust optimization naturally involve Wasserstein distances in their models of uncertainty, capturing data shifts or worst-case scenarios.
• Inspired by the success of the regularization of Wasserstein distances in optimal transport, we study in this paper the regularization of Wasserstein distributionally robust optimization.
• First, we derive a general strong duality result of regularized Wasserstein distributionally robust problems.