Distributionally Robust Stochastic Optimization with Wasserstein Distance
From MaRDI portal
Abstract: Distributionally robust stochastic optimization (DRSO) is an approach to optimization under uncertainty in which, instead of assuming that there is a known true underlying probability distribution, one hedges against a chosen set of distributions. In this paper we first point out that the set of distributions should be chosen to be appropriate for the application at hand, and that some of the choices that have been popular until recently are, for many applications, not good choices. We next consider sets of distributions that are within a chosen Wasserstein distance from a nominal distribution. Such a choice of sets has two advantages: (1) The resulting distributions hedged against are more reasonable than those resulting from other popular choices of sets. (2) The problem of determining the worst-case expectation over the resulting set of distributions has desirable tractability properties. We derive a strong duality reformulation of the corresponding DRSO problem and construct approximate worst-case distributions explicitly via the first-order optimality conditions of the dual problem. Our contributions are four-fold. (i) We identify necessary and sufficient conditions for the existence of a worst-case distribution, which are naturally related to the growth rate of the objective function. (ii) We show that the worst-case distributions resulting from an appropriate Wasserstein distance have a concise structure and a clear interpretation. (iii) Using this structure, we show that data-driven DRSO problems can be approximated to any accuracy by robust optimization problems, and thereby many DRSO problems become tractable by using tools from robust optimization. (iv) Our strong duality result holds in a very general setting. As examples, we show that it can be applied to infinite-dimensional process control and intensity estimation for point processes.
Recommendations
- Data-driven distributionally robust optimization using the Wasserstein metric: performance guarantees and tractable reformulations
- Regularization for Wasserstein distributionally robust optimization
- Wasserstein distributionally robust option pricing
- Distributionally Robust Two-Stage Stochastic Programming
- Distributions with maximum spread subject to Wasserstein distance constraints
Cited in
(64)- Data-driven risk-averse stochastic optimization with Wasserstein metric
- Emergency medical service location problem based on physical bounds using chance-constrained programming approach
- Risk measures under model uncertainty: a Bayesian viewpoint
- Finite-Sample Guarantees for Wasserstein Distributionally Robust Optimization: Breaking the Curse of Dimensionality
- Forward robust portfolio selection: the binomial case
- Distributional robustness, stochastic divergences, and the quadrangle of risk
- Optimal-transport satisficing with applications to capacitated hub location
- A dynamical neural network approach for distributionally robust chance-constrained Markov decision process
- Distributionally robust chance-constrained Markov decision processes with random payoff
- Limit distribution theory for smooth \(p\)-Wasserstein distances
- Isolated industrial micro-grid demand response with assembly process based on distributionally robust chance constraint
- Data-driven distributionally robust multiproduct pricing problems under pure characteristics demand models
- Residuals-based distributionally robust optimization with covariate information
- Distributionally robust optimization using optimal transport for Gaussian mixture models
- Distributionally robust portfolio optimization under marginal and copula ambiguity
- Distributionally robust optimization problem with probabilistic envelope constraints over Wasserstein ball
- Nonconcave stochastic optimal control in finite discrete time under model uncertainty
- Distributionally robust fractional optimization of probability of exceedance
- Distributionally robust optimization of the vehicle routing problem with uncertain customers
- A review of algorithms for distributionally robust optimization using statistical distances
- Distributionally robust risk evaluation with a causality constraint and structural information
- Outlier-robust nonsmooth stochastic optimization
- A parametric approach to the estimation of convex risk functionals based on Wasserstein distance
- Wasserstein distributionally robust optimization and its tractable regularization formulation
- Optimal transport regularized divergences: application to adversarial robustness
- Asymptotic Behavior of Adversarial Training Estimator under ℓ ∞ -Perturbation
- A distributionally robust machine learning model of simultaneous classification and feature selection under data uncertainty: theory, methods, and application to the identification of Alzheimer's disease using handwriting
- Sequential decision-making under uncertainty: a robust MDPs review
- Two-stage distributionally robust optimization with a finite support
- Distributionally robust tail bounds based on Wasserstein distance and f-divergence
- Gradient norm regularization second-order algorithms for solving nonconvex-strongly concave minimax problems
- k-submodular interdiction problems under distributional risk-receptiveness and robustness: application to machine learning
- Panda: partially approximate Newton methods for distributed minimax optimization with unbalanced dimensions
- Distributionally robust optimization and robust statistics
- A minimax approach to duality for linear distributional sensitivity testing
- Optimal transport-based distributionally robust optimization with polynomial uncertainty
- Robust n-agent heterogeneous investment-consumption game under -maxmin mean-variance-utility criterion
- Pareto front for two-stage distributionally robust optimization problems
- Mean robust optimization
- Nonlinear distributionally robust optimization
- ALSO-X \#: better convex approximations for distributionally robust chance constrained programs
- Optimizing distortion riskmetrics with distributional uncertainty
- Distributionally robust Gaussian process regression and Bayesian inverse problems
- An inexact Halpern iteration with application to distributionally robust optimization
- Distributionally robust optimization
- Robust satisficing model with Sinkhorn distance
- Discretization and quantification for distributionally robust optimization with decision-dependent ambiguity sets
- Integer programming approaches for distributionally robust chance constraints with adjustable risks
- Robustness assessment of climate policies towards carbon neutrality: a DRO-IAMS approach
- A reliable ensemble forecasting modeling approach for complex time series with distributionally robust optimization
- On regularization schemes for data-driven optimization based on Cressie–Read divergence and CVaR
- Adaptive dynamic programming and distributionally robust optimal control of linear stochastic system using the Wasserstein metric
- Robust knapsack ordering for a partially-informed newsvendor with budget constraint
- First-order conditions for optimization in the Wasserstein space
- Risk measures based on weak optimal transport
- Strategies with minimal norm are optimal for expected utility maximisation under high model ambiguity
- Efficient strategy synthesis for switched stochastic systems with distributional uncertainty
- The distributionally robust prediction error of the \(\sqrt{\mathrm{LASSO}}\) and related estimators
- Data-driven robust multiproduct pricing with fairness concerns
- Tailored Benders decomposition for two-stage distributionally robust combinatorial optimisation
- Numerical method for nonlinear Kolmogorov PDEs via sensitivity analysis
- Cone ordering in distributionally robust optimization with set-valued probabilities
- Convergent lifted Lasserre hierarchy of SDPs for minimizing expectation of piecewise polynomial loss over Wasserstein balls
- Robust estimation for kernel exponential families with smoothed total variation distances
This page was built for publication: Distributionally Robust Stochastic Optimization with Wasserstein Distance
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6199265)
