Quantifying Distributional Model Risk via Optimal Transport

DOI10.1287/moor.2018.0936zbMath1434.60113arXiv1604.01446OpenAlexW3124187518WikidataQ88977484 ScholiaQ88977484MaRDI QIDQ5219730

Karthyek R. A. Murthy, Jose H. Blanchet

Publication date: 12 March 2020

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

Full work available at URL: https://arxiv.org/abs/1604.01446

zbMATH Keywords

diffusion approximationsmodel riskruin probabilitiesKullback-Liebler divergencedistributionally robust optimization using Wasserstein distancesDRO

Mathematics Subject Classification ID

Applications of statistics to actuarial sciences and financial mathematics (62P05) General theory of stochastic processes (60G07) Limit theorems in probability theory (60F99)

Related Items (55)

On the Heavy-Tail Behavior of the Distributionally Robust Newsvendor ⋮ Learning models with uniform performance via distributionally robust optimization ⋮ Regularization via Mass Transportation ⋮ Model Uncertainty and Correctability for Directed Graphical Models ⋮ ALSO-X and ALSO-X+: Better Convex Approximations for Chance Constrained Programs ⋮ Frameworks and results in distributionally robust optimization ⋮ Dynamic optimization with side information ⋮ Tractable reformulations of two-stage distributionally robust linear programs over the type-\(\infty\) Wasserstein ball ⋮ Optimal Transport-Based Distributionally Robust Optimization: Structural Properties and Iterative Schemes ⋮ Distributionally robust profit opportunities ⋮ Distributionally Robust Two-Stage Stochastic Programming ⋮ Model-free bounds on value-at-risk using extreme value information and statistical distances ⋮ A Wasserstein distributionally robust chance constrained programming approach for emergency medical system planning problem ⋮ Sharing the value‐at‐risk under distributional ambiguity ⋮ Portfolio Optimization within a Wasserstein Ball ⋮ Sensitivity of Multiperiod Optimization Problems with Respect to the Adapted Wasserstein Distance ⋮ Chance-constrained optimization under limited distributional information: a review of reformulations based on sampling and distributional robustness ⋮ Unnamed Item ⋮ Regularization for Wasserstein distributionally robust optimization ⋮ Data-driven distributionally robust risk-averse two-stage stochastic linear programming over Wasserstein ball ⋮ Robustness to Incorrect System Models in Stochastic Control ⋮ Discrete Optimal Transport with Independent Marginals is #P-Hard ⋮ Towards well-generalizing meta-learning via adversarial task augmentation ⋮ Wasserstein perturbations of Markovian transition semigroups ⋮ Chance-constrained set covering with Wasserstein ambiguity ⋮ Worst-case moments under partial ambiguity ⋮ Asymptotic Analysis of a Multiclass Queueing Control Problem Under Heavy Traffic with Model Uncertainty ⋮ Distributionally Robust Strategy Synthesis for Switched Stochastic Systems ⋮ Adversarial classification via distributional robustness with Wasserstein ambiguity ⋮ Recovering Best Statistical Guarantees via the Empirical Divergence-Based Distributionally Robust Optimization ⋮ Optimization-Based Calibration of Simulation Input Models ⋮ On distributionally robust chance constrained programs with Wasserstein distance ⋮ Robust arbitrage conditions for financial markets ⋮ Recovering Brownian and jump parts from high-frequency observations of a Lévy process ⋮ Implementable coupling of Lévy process and Brownian motion ⋮ Robust Actuarial Risk Analysis ⋮ Extended Laplace principle for empirical measures of a Markov chain ⋮ Statistics of Robust Optimization: A Generalized Empirical Likelihood Approach ⋮ Distributionally Robust Stochastic Dual Dynamic Programming ⋮ Robust quantile estimation under bivariate extreme value models ⋮ Limits of random walks with distributionally robust transition probabilities ⋮ Controlling risk and demand ambiguity in newsvendor models ⋮ Robust Wasserstein profile inference and applications to machine learning ⋮ Simulation methods for robust risk assessment and the distorted mix approach ⋮ Sample Out-of-Sample Inference Based on Wasserstein Distance ⋮ On linear optimization over Wasserstein balls ⋮ Distributionally robust bottleneck combinatorial problems: uncertainty quantification and robust decision making ⋮ Distributionally robust chance-constrained programs with right-hand side uncertainty under Wasserstein ambiguity ⋮ Multistage distributionally robust mixed-integer programming with decision-dependent moment-based ambiguity sets ⋮ Robustness of stochastic programs with endogenous randomness via contamination ⋮ Formulation and properties of a divergence used to compare probability measures without absolute continuity ⋮ Toward theoretical understandings of robust Markov decision processes: sample complexity and asymptotics ⋮ Tight bounds for a class of data-driven distributionally robust risk measures ⋮ Robustness in the Optimization of Risk Measures ⋮ Distributionally Robust Inverse Covariance Estimation: The Wasserstein Shrinkage Estimator

Uses Software

• ROME

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Robust option pricing
• Data-driven chance constrained stochastic program
• On the rate of convergence in Wasserstein distance of the empirical measure
• On general minimax theorems
• On the optimality of threshold control in queues with model uncertainty
• Stochastic optimal control. The discrete time case
• Ruin problems with compounding assets
• Mass transportation problems. Vol. 1: Theory. Vol. 2: Applications
• Optimal transportation and applications. Lectures given at the C. I. M. E. summer school, Martina Franca, Italy, September 2--8, 2001
• Data-driven distributionally robust optimization using the Wasserstein metric: performance guarantees and tractable reformulations
• Likelihood robust optimization for data-driven problems
• Robust properties of risk-sensitive control
• A framework for optimization under ambiguity
• Convergence of latent mixing measures in finite and infinite mixture models
• An embedding of compensated compound Poisson processes with applications to local times
• Data-driven risk-averse stochastic optimization with Wasserstein metric
• Unbounded mappings and weak convergence of measures
• Ambiguous chance constrained problems and robust optimization
• On Stein's factors for Poisson approximation in Wasserstein distance
• Optimal Proportional Reinsurance Policies in a Dynamic Setting
• Stochastic-Process Limits
• MEASURING DISTRIBUTION MODEL RISK
• Path-Space Information Bounds for Uncertainty Quantification and Sensitivity Analysis of Stochastic Dynamics
• Robust Sensitivity Analysis for Stochastic Systems
• Robust risk measurement and model risk
• Distributionally Robust Convex Optimization
• Distributionally Robust Optimization Under Moment Uncertainty with Application to Data-Driven Problems
• Distributionally Robust Optimization and Its Tractable Approximations
• Relative Entropy, Exponential Utility, and Robust Dynamic Pricing
• Robust Queueing Theory
• Robust Bounds on Risk-Sensitive Functionals via Rényi Divergence
• The Price of Robustness
• Optimal proportional reinsurance policies for diffusion models
• Transport Inequalities. A Survey
• Fatou's Lemma for Weakly Converging Probabilities
• Distinguishing and integrating aleatoric and epistemic variation in uncertainty quantification
• Robust Control of Markov Decision Processes with Uncertain Transition Matrices
• Ambiguity in portfolio selection
• Diffusion approximations in collective risk theory
• Robust Dynamic Programming

This page was built for publication: Quantifying Distributional Model Risk via Optimal Transport