Doubly Robust Data-Driven Distributionally Robust Optimization
This work addresses the challenge of enhancing generalization for machine learning practitioners, though it appears incremental as it builds on existing distributionally robust optimization frameworks.
The authors tackled the problem of improving generalization in machine learning by proposing a doubly robust data-driven distributionally robust optimization method, which reduces testing error compared to state-of-the-art classifiers across various datasets.
Data-driven Distributionally Robust Optimization (DD-DRO) via optimal transport has been shown to encompass a wide range of popular machine learning algorithms. The distributional uncertainty size is often shown to correspond to the regularization parameter. The type of regularization (e.g. the norm used to regularize) corresponds to the shape of the distributional uncertainty. We propose a data-driven robust optimization methodology to inform the transportation cost underlying the definition of the distributional uncertainty. We show empirically that this additional layer of robustification, which produces a method we called doubly robust data-driven distributionally robust optimization (DD-R-DRO), allows to enhance the generalization properties of regularized estimators while reducing testing error relative to state-of-the-art classifiers in a wide range of data sets.