Residuals-based distributionally robust optimization with covariate information

Kannan, Rohit; Bayraksan, Güzin; Luedtke, James R.

doi:10.1007/s10107-023-02014-7

Residuals-based distributionally robust optimization with covariate information

Journal Article · Tue Sep 26 00:00:00 EDT 2023 · Mathematical Programming

DOI:https://doi.org/10.1007/s10107-023-02014-7· OSTI ID:2426805

^[1]; ^[2]; Luedtke, James R. ^[3]

Los Alamos National Laboratory (LANL), Los Alamos, NM (United States)
The Ohio State Univ., Columbus, OH (United States)
Univ. of Wisconsin, Madison, WI (United States)

We consider data-driven approaches that integrate a machine learning prediction model within distributionally robust optimization (DRO) given limited joint observations of uncertain parameters and covariates. Our framework is flexible in the sense that it can accommodate a variety of regression setups and DRO ambiguity sets. We investigate asymptotic and finite sample properties of solutions obtained using Wasserstein, sample robust optimization, and phi-divergence-based ambiguity sets within our DRO formulations, and explore cross-validation approaches for sizing these ambiguity sets. Through numerical experiments, we validate our theoretical results, study the effectiveness of our approaches for sizing ambiguity sets, and illustrate the benefits of our DRO formulations in the limited data regime even when the prediction model is misspecified.

View Accepted Manuscript (DOE)

Research Organization:: Los Alamos National Laboratory (LANL), Los Alamos, NM (United States)

Sponsoring Organization:: USDOE Laboratory Directed Research and Development (LDRD) Program; USDOE Office of Science (SC), Advanced Scientific Computing Research (ASCR)

Grant/Contract Number:: 89233218CNA000001

OSTI ID:: 2426805

Alternate ID(s):: OSTI ID: 2423773

Report Number(s):: LA-UR--22-24176

Journal Information:: Mathematical Programming, Journal Name: Mathematical Programming Journal Issue: 1-2 Vol. 207; ISSN 0025-5610

Publisher:: SpringerCopyright Statement

Country of Publication:: United States

Language:: English

References (40)

On the rate of convergence in Wasserstein distance of the empirical measure Fournier, Nicolas; Guillin, Arnaud Probability Theory and Related Fields, Vol. 162, Issue 3-4 https://doi.org/10.1007/s00440-014-0583-7	journal	October 2014
Data-driven distributionally robust optimization using the Wasserstein metric: performance guarantees and tractable reformulations Mohajerin Esfahani, Peyman; Kuhn, Daniel Mathematical Programming, Vol. 171, Issue 1-2 https://doi.org/10.1007/s10107-017-1172-1	journal	July 2017
Robust sample average approximation Bertsimas, Dimitris; Gupta, Vishal; Kallus, Nathan Mathematical Programming, Vol. 171, Issue 1-2 https://doi.org/10.1007/s10107-017-1174-z	journal	June 2017
Bootstrap robust prescriptive analytics Bertsimas, Dimitris; Van Parys, Bart Mathematical Programming, Vol. 195, Issue 1-2 https://doi.org/10.1007/s10107-021-01679-2	journal	June 2021
Distributionally robust stochastic programs with side information based on trimmings Esteban-Pérez, Adrián; Morales, Juan M. Mathematical Programming, Vol. 195, Issue 1-2 https://doi.org/10.1007/s10107-021-01724-0	journal	November 2021
Predictive stochastic programming Deng, Yunxiao; Sen, Suvrajeet Computational Management Science, Vol. 19, Issue 1 https://doi.org/10.1007/s10287-021-00400-0	journal	July 2021
Monte Carlo bounding techniques for determining solution quality in stochastic programs Mak, Wai-Kei; Morton, David P.; Wood, R. Kevin Operations Research Letters, Vol. 24, Issue 1-2 https://doi.org/10.1016/S0167-6377(98)00054-6	journal	February 1999
Conditional value-at-risk for general loss distributions Rockafellar, R. Tyrrell; Uryasev, Stanislav Journal of Banking & Finance, Vol. 26, Issue 7 https://doi.org/10.1016/S0378-4266(02)00271-6	journal	July 2002
Dynamic optimization with side information Bertsimas, Dimitris; McCord, Christopher; Sturt, Bradley European Journal of Operational Research, Vol. 304, Issue 2 https://doi.org/10.1016/j.ejor.2022.03.030	journal	January 2023
Generating random correlation matrices based on vines and extended onion method Lewandowski, Daniel; Kurowicka, Dorota; Joe, Harry Journal of Multivariate Analysis, Vol. 100, Issue 9 https://doi.org/10.1016/j.jmva.2009.04.008	journal	October 2009
Distributionally robust optimization with correlated data from vector autoregressive processes Dou, Xialiang; Anitescu, Mihai Operations Research Letters, Vol. 47, Issue 4 https://doi.org/10.1016/j.orl.2019.04.005	journal	July 2019
Tractable reformulations of two-stage distributionally robust linear programs over the type-∞ Wasserstein ball Xie, Weijun Operations Research Letters, Vol. 48, Issue 4 https://doi.org/10.1016/j.orl.2020.06.003	journal	July 2020
Robust Wasserstein profile inference and applications to machine learning Blanchet, Jose; Kang, Yang; Murthy, Karthyek Journal of Applied Probability, Vol. 56, Issue 3 https://doi.org/10.1017/jpr.2019.49	journal	September 2019
Generalization bounds for regularized portfolio selection with market side information Bazier-Matte, Thierry; Delage, Erick INFOR: Information Systems and Operational Research, Vol. 58, Issue 2 https://doi.org/10.1080/03155986.2020.1730675	journal	April 2020
Ambiguity in portfolio selection Pflug, Georg; Wozabal, David Quantitative Finance, Vol. 7, Issue 4 https://doi.org/10.1080/14697680701455410	journal	August 2007
Confidence regions in Wasserstein distributionally robust estimation Blanchet, Jose; Murthy, Karthyek; Si, Nian Biometrika, Vol. 109, Issue 2 https://doi.org/10.1093/biomet/asab026	journal	April 2021
Data-Driven Ambiguity Sets With Probabilistic Guarantees for Dynamic Processes Boskos, Dimitris; Cortes, Jorge; Martinez, Sonia IEEE Transactions on Automatic Control, Vol. 66, Issue 7 https://doi.org/10.1109/TAC.2020.3014098	journal	July 2021
Julia: A Fresh Approach to Numerical Computing Bezanson, Jeff; Edelman, Alan; Karpinski, Stefan SIAM Review, Vol. 59, Issue 1 https://doi.org/10.1137/141000671	journal	January 2017
JuMP: A Modeling Language for Mathematical Optimization Dunning, Iain; Huchette, Joey; Lubin, Miles SIAM Review, Vol. 59, Issue 2 https://doi.org/10.1137/15M1020575	journal	January 2017
Decomposition Algorithms for Two-Stage Distributionally Robust Mixed Binary Programs Bansal, Manish; Huang, Kuo-Ling; Mehrotra, Sanjay SIAM Journal on Optimization, Vol. 28, Issue 3 https://doi.org/10.1137/17M1115046	journal	January 2018
Data-Driven Stochastic Programming Using Phi-Divergences Bayraksan, Güzin; Love, David K. The Operations Research Revolution https://doi.org/10.1287/educ.2015.0134	book	September 2015
Robust Solutions of Optimization Problems Affected by Uncertain Probabilities Ben-Tal, Aharon; den Hertog, Dick; De Waegenaere, Anja Management Science, Vol. 59, Issue 2 https://doi.org/10.1287/mnsc.1120.1641	journal	February 2013
From Predictive to Prescriptive Analytics Bertsimas, Dimitris; Kallus, Nathan Management Science, Vol. 66, Issue 3 https://doi.org/10.1287/mnsc.2018.3253	journal	March 2020
A Data-Driven Approach to Multistage Stochastic Linear Optimization Bertsimas, Dimitris; Shtern, Shimrit; Sturt, Bradley Management Science https://doi.org/10.1287/mnsc.2022.4352	journal	March 2022
A Distributional Interpretation of Robust Optimization Xu, Huan; Caramanis, Constantine; Mannor, Shie Mathematics of Operations Research, Vol. 37, Issue 1 https://doi.org/10.1287/moor.1110.0531	journal	February 2012
Robust Sensitivity Analysis for Stochastic Systems Lam, Henry Mathematics of Operations Research, Vol. 41, Issue 4 https://doi.org/10.1287/moor.2015.0776	journal	November 2016
Statistics of Robust Optimization: A Generalized Empirical Likelihood Approach Duchi, John C.; Glynn, Peter W.; Namkoong, Hongseok Mathematics of Operations Research, Vol. 46, Issue 3 https://doi.org/10.1287/moor.2020.1085	journal	August 2021
Distributionally Robust Stochastic Optimization with Wasserstein Distance Gao, Rui; Kleywegt, Anton Mathematics of Operations Research, Vol. 48, Issue 2 https://doi.org/10.1287/moor.2022.1275	journal	May 2023
Dynamic Procurement of New Products with Covariate Information: The Residual Tree Method Ban, Gah-Yi; Gallien, Jérémie; Mersereau, Adam J. Manufacturing & Service Operations Management, Vol. 21, Issue 4 https://doi.org/10.1287/msom.2018.0725	journal	October 2019
Conic Programming Reformulations of Two-Stage Distributionally Robust Linear Programs over Wasserstein Balls Hanasusanto, Grani A.; Kuhn, Daniel Operations Research, Vol. 66, Issue 3 https://doi.org/10.1287/opre.2017.1698	journal	June 2018
The Big Data Newsvendor: Practical Insights from Machine Learning Ban, Gah-Yi; Rudin, Cynthia Operations Research, Vol. 67, Issue 1 https://doi.org/10.1287/opre.2018.1757	journal	January 2019
Calibration of Distributionally Robust Empirical Optimization Models Gotoh, Jun‐ya; Kim, Michael Jong; Lim, Andrew E. B. Operations Research, Vol. 69, Issue 5 https://doi.org/10.1287/opre.2020.2041	journal	September 2021
Technical Note—Two-Stage Sample Robust Optimization Bertsimas, Dimitris; Shtern, Shimrit; Sturt, Bradley Operations Research, Vol. 70, Issue 1 https://doi.org/10.1287/opre.2020.2096	journal	January 2022
Finite-Sample Guarantees for Wasserstein Distributionally Robust Optimization: Breaking the Curse of Dimensionality Gao, Rui Operations Research, Vol. 71, Issue 6 https://doi.org/10.1287/opre.2022.2326	journal	November 2023
Wasserstein Distributionally Robust Optimization and Variation Regularization Gao, Rui; Chen, Xi; Kleywegt, Anton J. Operations Research, Vol. 72, Issue 3 https://doi.org/10.1287/opre.2022.2383	journal	May 2024
Regularization Paths for Generalized Linear Models via Coordinate Descent Friedman, Jerome; Hastie, Trevor; Tibshirani, Robert Journal of Statistical Software, Vol. 33, Issue 1 https://doi.org/10.18637/jss.v033.i01	journal	January 2010
Optimization of conditional value-at-risk Rockafellar, R. Tyrrell; Uryasev, Stanislav The Journal of Risk, Vol. 2, Issue 3 https://doi.org/10.21314/JOR.2000.038	journal	January 2000
Data-Driven Ambiguity Sets for Linear Systems Under Disturbances and Noisy Observations Boskos, Dimitris; Cortes, Jorge; Martinez, Sonia 2020 American Control Conference (ACC) https://doi.org/10.23919/ACC45564.2020.9147334	conference	July 2020
On the Rate of Convergence of Empirical Measures in ∞-transportation Distance García Trillos, Nicolás; Slepčev, Dejan Canadian Journal of Mathematics, Vol. 67, Issue 6 https://doi.org/10.4153/CJM-2014-044-6	journal	December 2015
Frameworks and Results in Distributionally Robust Optimization Rahimian, Hamed; Mehrotra, Sanjay Open Journal of Mathematical Optimization, Vol. 3 https://doi.org/10.5802/ojmo.15	journal	July 2022

Similar Records

Residuals-based distributionally robust optimization with covariate information

Technical Report · Tue May 03 00:00:00 EDT 2022 · OSTI ID:2377330

Revealing Decision Conservativeness Through Inverse Distributionally Robust Optimization

Journal Article · Thu May 30 00:00:00 EDT 2024 · IEEE Control Systems Letters · OSTI ID:2376667

Distributionally Robust Decision Making Leveraging Conditional Distributions

Conference · Mon Dec 05 23:00:00 EST 2022 · 2022 IEEE 61st Conference on Decision and Control (CDC) · OSTI ID:1989810

Related Subjects

97 MATHEMATICS AND COMPUTING
Data-driven stochastic programming
Mathematics
Wasserstein distance
convergence rate
covariates
distributionally robust optimization
large deviations
machine learning
phi-divergences

Residuals-based distributionally robust optimization with covariate information

Citation Formats

References (40)

Similar Records

Related Subjects