Large-Scale Non-convex Stochastic Constrained Distributionally Robust Optimization

arXiv:2404.01200v1 Announce Type: cross
Abstract: Distributionally robust optimization (DRO) is a powerful framework for training robust models against data distribution shifts. This paper focuses on constrained DRO, which has an explicit characterization of the robustness level. Existing studies on constrained DRO mostly focus on convex loss function, and exclude the practical and challenging case with non-convex loss function, e.g., neural network. This paper develops a stochastic algorithm and its performance analysis for non-convex constrained DRO. The computational complexity of our …

abstract arxiv cs.lg data distribution focus framework function loss optimization paper practical robust robust models robustness scale stat.ml stochastic studies training type