Nonlinear Distributionally Robust Optimization
This work addresses a theoretical and computational bottleneck in DRO for researchers and practitioners, though it appears incremental by building on existing methods.
The paper tackles the challenge of optimizing nonlinear functions in distributionally robust optimization (DRO) by proposing a new derivative concept based on Gateaux derivatives and a Frank-Wolfe algorithm, demonstrating convergence and validating results with numerical experiments on portfolio selection problems.
This article focuses on a class of distributionally robust optimization (DRO) problems where, unlike the growing body of the literature, the objective function is potentially nonlinear in the distribution. Existing methods to optimize nonlinear functions in probability space use the Frechet derivatives, which present theoretical and computational challenges. Motivated by this, we propose an alternative notion for the derivative and corresponding smoothness based on Gateaux (G)-derivative for generic risk measures. These concepts are explained via three running risk measure examples of variance, entropic risk, and risk on finite support sets. We then propose a G-derivative-based Frank-Wolfe (FW) algorithm for generic nonlinear optimization problems in probability spaces and establish its convergence under the proposed notion of smoothness in a completely norm-independent manner. We use the set-up of the FW algorithm to devise a methodology to compute a saddle point of the nonlinear DRO problem. Finally, we validate our theoretical results on two cases of the $entropic$ and $variance$ risk measures in the context of portfolio selection problems. In particular, we analyze their regularity conditions and "sufficient statistic", compute the respective FW-oracle in various settings, and confirm the theoretical outcomes through numerical validation.