Optimal Transport-Based Distributionally Robust Optimization: Structural Properties and Iterative Schemes

DOI10.1287/moor.2021.1178zbMath1489.90094arXiv1810.02403OpenAlexW3213876467MaRDI QIDQ5085150

Karthyek R. A. Murthy, Fan Zhang, Jose H. Blanchet

Publication date: 27 June 2022

Published in: Mathematics of Operations Research (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1810.02403

zbMATH Keywords

rate of convergencecomparative staticsstochastic gradient descentoptimal transportWasserstein distancesstrong convexitydistributionally robust optimizationadversarial

Mathematics Subject Classification ID

Numerical mathematical programming methods (65K05) Minimax problems in mathematical programming (90C47) Stochastic programming (90C15) Robustness in mathematical programming (90C17)

Related Items

Frameworks and results in distributionally robust optimization ⋮ Distributionally Robust Two-Stage Stochastic Programming ⋮ Regularization for Wasserstein distributionally robust optimization ⋮ Distributionally Robust Strategy Synthesis for Switched Stochastic Systems

Uses Software

• Saga

Cites Work

• Unnamed Item
• Convergence rate and averaging of nonlinear two-time-scale stochastic approximation algo\-rithms
• Stochastic optimal control. The discrete time case
• Data-driven distributionally robust optimization using the Wasserstein metric: performance guarantees and tractable reformulations
• On distributionally robust chance constrained programs with Wasserstein distance
• Data-driven risk-averse stochastic optimization with Wasserstein metric
• Decomposition algorithm for distributionally robust optimization using Wasserstein metric with an application to a class of regression models
• Stochastic optimization problems with nondifferentiable cost functionals
• Robust Stochastic Approximation Approach to Stochastic Programming
• Acceleration of Stochastic Approximation by Averaging
• Conic Programming Reformulations of Two-Stage Distributionally Robust Linear Programs over Wasserstein Balls
• Katyusha: the first direct acceleration of stochastic gradient methods
• Confidence regions in Wasserstein distributionally robust estimation
• Regularization via Mass Transportation
• Quantifying Distributional Model Risk via Optimal Transport
• Robust Wasserstein profile inference and applications to machine learning
• Efficient Line Search Methods for Convex Functions
• Envelope Theorems for Arbitrary Choice Sets
• A Stochastic Approximation Method

This page was built for publication: Optimal Transport-Based Distributionally Robust Optimization: Structural Properties and Iterative Schemes