Calibration of distributionally robust empirical optimization models

DOI10.1287/OPRE.2020.2041MaRDI QIDQ5031650zbMATH OpenOpenAlexFDO

Authors Jun-Ya Gotoh, Michael Jong Kim, Andrew Lim

Publication date 16 February 2022

Published in Operations Research (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1711.06565

zbMATH Keywords

calibrationdistributionally robust optimizationnonlinear programmingoptimizationrisksamplingsensitivitystatistics: datastochastic model applicationsstochastic programmingvariance reductionworst-case sensitivity

Mathematics Subject Classification ID

Robustness in mathematical programming (90C17)

Abstract: We study the out-of-sample properties of robust empirical optimization problems with smooth $phi$-divergence penalties and smooth concave objective functions, and develop a theory for data-driven calibration of the non-negative "robustness parameter" $delta$ that controls the size of the deviations from the nominal model. Building on the intuition that robust optimization reduces the sensitivity of the expected reward to errors in the model by controlling the spread of the reward distribution, we show that the first-order benefit of ``little bit of robustness" (i.e., $delta$ small, positive) is a significant reduction in the variance of the out-of-sample reward while the corresponding impact on the mean is almost an order of magnitude smaller. One implication is that substantial variance (sensitivity) reduction is possible at little cost if the robustness parameter is properly calibrated. To this end, we introduce the notion of a robust mean-variance frontier to select the robustness parameter and show that it can be approximated using resampling methods like the bootstrap. Our examples show that robust solutions resulting from "open loop" calibration methods (e.g., selecting a $90\mathrm{\%}$ confidence level regardless of the data and objective function) can be very conservative out-of-sample, while those corresponding to the robustness parameter that optimizes an estimate of the out-of-sample expected reward (e.g., via the bootstrap) with no regard for the variance are often insufficiently robust.

Recommendations

• scientific article; zbMATH DE number 7668294
• Statistics of robust optimization: a generalized empirical likelihood approach
• A distributional interpretation of robust optimization
• Adjusted robust mean-value-at-risk model: less conservative robust portfolios
• Data-driven robust optimization

Cites work

• A Bayesian risk approach to data-driven stochastic optimization: formulations and asymptotics
• Asymptotic Statistics
• Breast Cancer Diagnosis and Prognosis Via Linear Programming
• Characterization of the equivalence of robustification and regularization in linear and matrix regression
• Data-driven robust optimization
• Distributionally robust optimization under moment uncertainty with application to data-driven problems
• Lectures on stochastic programming. Modeling and theory.
• Robust empirical optimization is almost the same as mean-variance optimization
• Robust Regression and Lasso
• Robust sample average approximation
• Robust sensitivity analysis for stochastic systems

Cited in

(15)

• Bootstrap robust prescriptive analytics
• Robust calibration of numerical models based on relative regret
• Frameworks and results in distributionally robust optimization
• Robust empirical optimization is almost the same as mean-variance optimization
• A collaborative model calibration framework under uncertainty considering parameter distribution
• Robust Wasserstein profile inference and applications to machine learning
• A multistage distributionally robust optimization approach to water allocation under climate uncertainty
• Cardinality-constrained distributionally robust portfolio optimization
• Bayesian Distributionally Robust Optimization
• Data-driven aerodynamic shape design with distributionally robust optimization approaches
• A new distributionally robust reward-risk model for portfolio optimization
• Residuals-based distributionally robust optimization with covariate information
• Tractable fish growth models considering individual differences with an application to the fish \textit{Plecoglossus altivelis}
• Distributionally robust optimization
• Risk-adaptive approaches to stochastic optimization: a survey

Describes a project that uses

Uses Software

• UCI

This page was built for publication: Calibration of distributionally robust empirical optimization models

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5031650)