Flow-based Distributionally Robust Optimization

arXiv:2310.19253v3 Announce Type: replace
Abstract: We present a computationally efficient framework, called $\texttt{FlowDRO}$, for solving flow-based distributionally robust optimization (DRO) problems with Wasserstein uncertainty sets while aiming to find continuous worst-case distribution (also called the Least Favorable Distribution, LFD) and sample from it. The requirement for LFD to be continuous is so that the algorithm can be scalable to problems with larger sample sizes and achieve better generalization capability for the induced robust algorithms. To tackle the computationally challenging infinitely …

abstract algorithm arxiv case continuous cs.lg distribution flow framework least optimization robust sample stat.me stat.ml the algorithm type uncertainty