Distributionally robust stochastic programs with side information based on trimmings

DOI10.1007/S10107-021-01724-0zbMATH Open1504.90077arXiv2009.10592OpenAlexW3216535839MaRDI QIDQ2089796FDOQ2089796

Authors: Yanyan Li 

Publication date: 24 October 2022

Published in: Mathematical Programming. Series A. Series B (Search for Journal in Brave)

Abstract: We consider stochastic programs conditional on some covariate information, where the only knowledge of the possible relationship between the uncertain parameters and the covariates is reduced to a finite data sample of their joint distribution. By exploiting the close link between the notion of trimmings of a probability measure and the partial mass transportation problem, we construct a data-driven Distributionally Robust Optimization (DRO) framework to hedge the decision against the intrinsic error in the process of inferring conditional information from limited joint data. We show that our approach is computationally as tractable as the standard (without side information) Wasserstein-metric-based DRO and enjoys performance guarantees. Furthermore, our DRO framework can be conveniently used to address data-driven decision-making problems under contaminated samples and naturally produces distributionally robust versions of some local nonparametric predictive methods, such as Nadaraya-Watson kernel regression and $K$-nearest neighbors, which are often used in the context of conditional stochastic optimization. Finally, the theoretical results are illustrated using a single-item newsvendor problem and a portfolio allocation problem with side information.

Full work available at URL: https://arxiv.org/abs/2009.10592

Recommendations

• Distributionally robust optimization under moment uncertainty with application to data-driven problems
• Data-driven distributionally robust optimization using the Wasserstein metric: performance guarantees and tractable reformulations
• Robust sample average approximation
• scientific article; zbMATH DE number 7668294
• Distributionally Robust Convex Optimization

zbMATH Keywords

portfolio optimizationnewsvendor problemside informationdistributionally robust optimizationpartial mass transportation problemtrimmings

Mathematics Subject Classification ID

Stochastic programming (90C15) Minimax problems in mathematical programming (90C47)

Cites Work

• Optimal transport for applied mathematicians. Calculus of variations, PDEs, and modeling
• On Choosing and Bounding Probability Metrics
• Title not available (Why is that?)
• On the rate of convergence in Wasserstein distance of the empirical measure
• On general minimax theorems
• Uniqueness and approximate computation of optimal incomplete transportation plans
• Rates of convergence for partial mass problems
• Similarity of samples and trimming
• Probability, Random Processes, and Ergodic Properties
• Lectures on the nearest neighbor method
• Data-driven distributionally robust optimization using the Wasserstein metric: performance guarantees and tractable reformulations
• A data-driven newsvendor problem: from data to decision
• The big data newsvendor: practical insights from machine learning
• Technical note -- two-stage sample robust optimization

Cited In (3)

• Residuals-based distributionally robust optimization with covariate information
• Frameworks and results in distributionally robust optimization
• Contextual robust optimisation with uncertainty quantification

Uses Software

• GitHub

This page was built for publication: Distributionally robust stochastic programs with side information based on trimmings

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2089796)