Regularization for Wasserstein distributionally robust optimization
From MaRDI portal
Abstract: Optimal transport has recently proved to be a useful tool in various machine learning applications needing comparisons of probability measures. Among these, applications of distributionally robust optimization naturally involve Wasserstein distances in their models of uncertainty, capturing data shifts or worst-case scenarios. Inspired by the success of the regularization of Wasserstein distances in optimal transport, we study in this paper the regularization of Wasserstein distributionally robust optimization. First, we derive a general strong duality result of regularized Wasserstein distributionally robust problems. Second, we refine this duality result in the case of entropic regularization and provide an approximation result when the regularization parameters vanish.
Recommendations
- Semidual regularized optimal transport
- Robust Wasserstein profile inference and applications to machine learning
- Regularization via mass transportation
- Data-driven distributionally robust optimization using the Wasserstein metric: performance guarantees and tractable reformulations
- Optimal transport-based distributionally robust optimization: structural properties and iterative schemes
Cites work
- Applied functional analysis. Functional analysis, Sobolev spaces and elliptic differential equations
- Computational optimal transport. With applications to data sciences
- Convergence of entropic schemes for optimal transport and gradient flows
- Convex optimization in normed spaces. Theory, methods and examples
- Data-driven distributionally robust optimization using the Wasserstein metric: performance guarantees and tractable reformulations
- Duality in Vector Optimization
- scientific article; zbMATH DE number 1807400 (Why is no real title available?)
- scientific article; zbMATH DE number 3886543 (Why is no real title available?)
- scientific article; zbMATH DE number 1022519 (Why is no real title available?)
- scientific article; zbMATH DE number 1022658 (Why is no real title available?)
- scientific article; zbMATH DE number 1909499 (Why is no real title available?)
- Interpolation theory
- Measure theory. Vol. I and II
- Moment inequalities for functions of independent random variables
- Optimal bounds between f-divergences and integral probability metrics
- Optimal filtering equations in state space model of the two factors mean reverting Ornstein-Uhlenbech process
- Optimal Transport
- Optimal transport for applied mathematicians. Calculus of variations, PDEs, and modeling
- Optimal transport-based distributionally robust optimization: structural properties and iterative schemes
- Optimal transport: discretization and algorithms
- Orlicz spaces and modular spaces
- Primal-dual extragradient methods for nonlinear nonsmooth PDE-constrained optimization
- Probability theory. A comprehensive course
- Quantifying distributional model risk via optimal transport
- Random measures, theory and applications
- Regularization via mass transportation
- Robust Wasserstein profile inference and applications to machine learning
- Topological duals of locally convex function spaces
- Variational Analysis
Cited in
(18)- Data-driven distributionally robust optimization using the Wasserstein metric: performance guarantees and tractable reformulations
- On linear optimization over Wasserstein balls
- On the regularized risk of distributionally robust learning over deep neural networks
- Decomposition algorithm for distributionally robust optimization using Wasserstein metric with an application to a class of regression models
- Distributionally robust chance constrained SVM model with _2-Wasserstein distance
- Adversarial classification via distributional robustness with Wasserstein ambiguity
- Optimal transport-based distributionally robust optimization: structural properties and iterative schemes
- Regularization via mass transportation
- Robust Wasserstein profile inference and applications to machine learning
- Wasserstein Regression
- Finite-Sample Guarantees for Wasserstein Distributionally Robust Optimization: Breaking the Curse of Dimensionality
- Distributionally Robust Stochastic Optimization with Wasserstein Distance
- Regularized distributionally robust optimization with application to the index tracking problem
- Wasserstein distributionally robust optimization and variation regularization
- Optimal transport regularized divergences: application to adversarial robustness
- Distributionally robust optimization and robust statistics
- Distributionally robust optimization
- Robust satisficing model with Sinkhorn distance
This page was built for publication: Regularization for Wasserstein distributionally robust optimization
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6138461)
