Data-driven distributionally robust optimization over a network via distributed semi-infinite programming

Abstract

This paper focuses on solving a data-driven distributionally robust optimization problem over a network of agents. The agents aim to minimize the worst-case expected cost computed over a Wasserstein ambiguity set that is centered at the empirical distribution. The samples of the uncertainty are distributed across the agents. Our approach consists of reformulating the problem as a semi-infinite program and then designing a distributed algorithm that solves a generic semiinfinite problem that has the same information structure as the reformulated problem. In particular, the decision variables consist of both local ones that agents are free to optimize over and global ones where they need to agree on. Our distributed algorithm is an iterative procedure that combines the notions of distributed ADMM and the cutting-surface method. We show that the iterates converge asymptotically to a solution of the distributionally robust problem to any pre-specified accuracy. Simulations illustrate our results. IEEE 61st Conference on Decision and Control (CDC)

Capture, Propagate, and Control Distributional Uncertainty

“…More recently, Wasserstein ambiguity sets, and more generally optimal transport, penetrated the control community, with application in uncertainty quantification in dynamical systems [8], [9], model predictive control [10]- [12], distribution steering [13], optimal control [14], multi-agent stochastic optimization [15], [16], linear quadratic differential games [17], probability/multi-agent control [18], and filtering [19]- [22], to name a few. In this paper, we demonstrate that Optimal Transport (OT) ambiguity sets, which encompass Wasserstein ambiguity sets, are also easy to propagate.…”