Corpus ID: 226222395

Wasserstein Distributionally Robust Optimization and Variation Regularization.

  title={Wasserstein Distributionally Robust Optimization and Variation Regularization.},
  author={R. Gao and Xi Chen and A. Kleywegt},
  journal={arXiv: Learning},
  • R. Gao, Xi Chen, A. Kleywegt
  • Published 2017
  • Computer Science, Mathematics
  • arXiv: Learning
  • Wasserstein distributionally robust optimization (DRO) has recently achieved empirical success for various applications in operations research and machine learning, owing partly to its regularization effect. Although connection between Wasserstein DRO and regularization has been established in several settings, existing results often require restrictive assumptions, such as smoothness or convexity, that are not satisfied for many problems. In this paper, we develop a general theory on the… CONTINUE READING
    12 Citations
    Distributionally Robust Optimization and Generalization in Kernel Methods
    • 18
    • PDF
    Incorporating Unlabeled Data into Distributionally Robust Learning
    • 3
    • PDF
    Adversarial Risk via Optimal Transport and Optimal Couplings
    • 14
    • PDF
    Robust GANs against Dishonest Adversaries
    • 1
    • PDF
    Robust risk aggregation with neural networks
    • 8
    • PDF


    Robust Wasserstein profile inference and applications to machine learning
    • 119
    • PDF
    Regularization via Mass Transportation
    • 68
    • PDF
    Distributionally Robust Logistic Regression
    • 129
    • PDF
    Improved Training of Wasserstein GANs
    • 3,942
    • PDF
    Robust Regression and Lasso
    • 216
    • PDF
    Adam: A Method for Stochastic Optimization
    • 58,852
    • PDF