On the Tradeoff Between Distributional Belief and Ambiguity: Conservatism, Finite-Sample Guarantees, and Asymptotic Properties

References

• Banholzer D, Fliege J, Werner R (2022) On rates of convergence for sample average approximations in the almost sure sense and in mean. Math. Programming 191(1):307–345.Google Scholar
• Bayraksan G, Love DK (2015) Data-driven stochastic programming using phi-divergences. INFORMS TutORials in Operations Research (INFORMS, Catonsville, MD), 1–19.Google Scholar
• Ben-Tal A, Den Hertog D, De Waegenaere A, Melenberg B, Rennen G (2013) Robust solutions of optimization problems affected by uncertain probabilities. Management Sci. 59(2):341–357.Link, Google Scholar
• Bertsimas D, Kallus N (2020) From predictive to prescriptive analytics. Management Sci. 66(3):1025–1044.Link, Google Scholar
• Bertsimas D, Gupta V, Kallus N (2018) Robust sample average approximation. Math. Programming 171(1):217–282.Google Scholar
• Birge JR, Louveaux F (2011) Introduction to Stochastic Programming (Springer Science & Business Media, New York).Google Scholar
• Blanchet J, Shapiro A (2023) Statistical limit theorems in distributionally robust optimization. Corlu CG, Hunter SR, Lam H, Onggo BS, Shortle J, Biller B, eds. Proc. Winter Simulation Conf. (IEEE, Piscataway, NJ), 31–45.Google Scholar
• Blanchet JH, Glynn PW, Pei Y (2019) Unbiased multilevel Monte Carlo: Stochastic optimization, steady-state simulation, quantiles, and other applications. Preprint, submitted April 22, https://arxiv.org/abs/1904.09929.Google Scholar
• Blanchet J, Murthy K, Nguyen VA (2021) Statistical analysis of Wasserstein distributionally robust estimators. Tutorials in Operations Research: Emerging Optimization Methods and Modeling Techniques with Applications (INFORMS, Catonsville, MD), 227–254.Link, Google Scholar
• Chen L, He S, Zhang S (2011) Tight bounds for some risk measures, with applications to robust portfolio selection. Oper. Res. 59(4):847–865.Link, Google Scholar
• Chen Z, Ma W, Ji B (2025) Data-driven approximation of distributionally robust chance constraints using Bayesian credible intervals. OR Spectrum, 1–41.Google Scholar
• Das B, Dhara A, Natarajan K (2021) On the heavy-tail behavior of the distributionally robust newsvendor. Oper. Res. 69(4):1077–1099.Link, Google Scholar
• de Klerk E, Kuhn D, Postek K (2020) Distributionally robust optimization with polynomial densities: Theory, models and algorithms. Math. Programming 181(2):265–296.Google Scholar
• Delage E, Ye Y (2010) Distributionally robust optimization under moment uncertainty with application to data-driven problems. Oper. Res. 58(3):595–612.Link, Google Scholar
• Dentcheva D, Lin Y (2022) Bias reduction in sample-based optimization. SIAM J. Optim. 32(1):130–151.Google Scholar
• Ding KW, Huang NJ, Wang L (2024) Globalized distributionally robust optimization problems under the moment-based framework. Optimization 73(9):2845–2883.Google Scholar
• Duchi JC, Namkoong H (2021) Learning models with uniform performance via distributionally robust optimization. Ann. Statist. 49(3):1378–1406.Google Scholar
• Duchi JC, Glynn PW, Namkoong H (2021) Statistics of robust optimization: A generalized empirical likelihood approach. Math. Oper. Res. 46(3):946–969.Link, Google Scholar
• Eichhorn A, Römisch W (2007) Stochastic integer programming: Limit theorems and confidence intervals. Math. Oper. Res. 32(1):118–135.Link, Google Scholar
• Fabozzi FJ, Focardi SM, Kolm PN, Pachamanova DA (2007) Robust Portfolio Optimization and Management (John Wiley & Sons, Hoboken, NJ).Google Scholar
• Gallego G, Moon I (1993) The distribution free newsboy problem: Review and extensions. J. Oper. Res. Soc. 44(8):825–834.Google Scholar
• Gao R (2023) Finite-sample guarantees for Wasserstein distributionally robust optimization: Breaking the curse of dimensionality. Oper. Res. 71(6):2291–2306.Google Scholar
• Gao R, Kleywegt A (2023) Distributionally robust stochastic optimization with Wasserstein distance. Math. Oper. Res. 48(2):603–655.Google Scholar
• Goh J, Sim M (2010) Distributionally robust optimization and its tractable approximations. Oper. Res. 58(4-part-1):902–917.Link, Google Scholar
• Gorissen BL, Yanıkoğlu İ, Den Hertog D (2015) A practical guide to robust optimization. Omega 53:124–137.Google Scholar
• Gotoh J, Kim MJ, Lim AE (2021) Calibration of distributionally robust empirical optimization models. Oper. Res. 69(5):1630–1650.Link, Google Scholar
• Guigues V, Krätschmer V, Shapiro A (2018) A central limit theorem and hypotheses testing for risk-averse stochastic programs. SIAM J. Optim. 28(2):1337–1366.Google Scholar
• Hanasusanto GA, Roitch V, Kuhn D, Wiesemann W (2015) A distributionally robust perspective on uncertainty quantification and chance constrained programming. Math. Programming 151(1):35–62.Google Scholar
• Homem-de Mello T, Bayraksan G (2014) Monte Carlo sampling-based methods for stochastic optimization. Survey Oper. Res. Management Sci. 19(1):56–85.Google Scholar
• Huang R, Qu S, Yang X, Xu F, Xu Z, Zhou W (2021) Sparse portfolio selection with uncertain probability distribution. Appl. Intelligence 51(10):6665–6684.Google Scholar
• Huber PJ (1964) Robust estimation of a location parameter. Ann. Math. Statist. 35(1):73–101.Google Scholar
• Iyengar G, Lam H, Wang T (2022) Hedging complexity in generalization via a parametric distributionally robust optimization framework. Preprint, submitted December 3, https://arxiv.org/abs/2212.01518.Google Scholar
• Kakouris I, Rustem B (2014) Robust portfolio optimization with copulas. Eur. J. Oper. Res. 235(1):28–37.Google Scholar
• Kim S, Pasupathy R, Henderson SG (2015) A guide to sample average approximation. Fu MC, ed. Handbook of Simulation Optimization (Springer, New York), 207–243.Google Scholar
• Kuhn D, Shafiee S, Wiesemann W (2024) Distributionally robust optimization. Preprint, submitted November 4, https://arxiv.org/abs/2411.02549.Google Scholar
• Kuhn D, Mohajerin Esfahani P, Nguyen VA, Shafieezadeh-Abadeh S (2019) Wasserstein distributionally robust optimization: Theory and applications in machine learning. Operations Research & Management Science in the Age of Analytics (INFORMS, Catonsville, MD), 130–166.Link, Google Scholar
• Lam H (2019) Recovering best statistical guarantees via the empirical divergence-based distributionally robust optimization. Oper. Res. 67(4):1090–1105.Abstract, Google Scholar
• Lam H (2021) On the impossibility of statistically improving empirical optimization: A second-order stochastic dominance perspective. Preprint, submitted May 27, https://arxiv.org/abs/2105.13419.Google Scholar
• Lam H (2022) A cheap bootstrap method for fast inference. Preprint, submitted January 31, https://arxiv.org/abs/2202.00090.Google Scholar
• Lam H, Liu Z, Zhang X (2021) Orthounimodal distributionally robust optimization: Representation, computation and multivariate extreme event applications. Preprint, submitted November 15, https://arxiv.org/abs/2111.07894.Google Scholar
• Li Y, Xing W (2024) Globalized distributionally robust optimization based on samples. J. Global Optim. 88(4):871–900.Google Scholar
• Li B, Jiang R, Mathieu JL (2019) Ambiguous risk constraints with moment and unimodality information. Math. Programming 173(1–2):151–192.Google Scholar
• Liu Y, Xu H (2013) Stability analysis of stochastic programs with second order dominance constraints. Math. Programming 142(1):435–460.Google Scholar
• Liu F, Chen Z, Wang S (2023a) Globalized distributionally robust counterpart. INFORMS J. Comput. 35(5):1120–1142.Google Scholar
• Liu Y, Pichler A, Xu H (2019) Discrete approximation and quantification in distributionally robust optimization. Math. Oper. Res. 44(1):19–37.Abstract, Google Scholar
• Liu Z, Van Parys BP, Lam H (2023b) Smoothed f-divergence distributionally robust optimization: Exponential rate efficiency and complexity-free calibration. Preprint, submitted June 24, https://arxiv.org/abs/2306.14041.Google Scholar
• Liu J, Wu J, Li B, Cui P (2022) Distributionally robust optimization with data geometry. Koyejo S, Mohamed S, Agarwal A, Belgrave D, Cho K, Oh A, eds. Proc. 36th Conf. Neural Inform. Processing Systems (Curran Associates Inc., Red Hook, NY), 33689–33701.Google Scholar
• Long DZ, Qi J, Zhang A (2024) Supermodularity in two-stage distributionally robust optimization. Management Sci. 70(3):1394–1409.Link, Google Scholar
• Mak WK, Morton DP, Wood RK (1999) Monte Carlo bounding techniques for determining solution quality in stochastic programs. Oper. Res. Lett. 24(1–2):47–56.Google Scholar
• Michel P, Hashimoto T, Neubig G (2021) Modeling the second player in distributionally robust optimization. Proc. Internat. Conf. Learn. Representations (Curran Associates Inc., Red Hook, NY).Google Scholar
• Michel P, Hashimoto T, Neubig G (2022) Distributionally robust models with parametric likelihood ratios. Proc. Internat. Conf. Learn. Representations (Curran Associates Inc., Red Hook, NY).Google Scholar
• Mohajerin Esfahani P, Kuhn D (2018) Data-driven distributionally robust optimization using the Wasserstein metric: Performance guarantees and tractable reformulations. Math. Programming 171(1):115–166.Google Scholar
• Nie J, Yang L, Zhong S, Zhou G (2023) Distributionally robust optimization with moment ambiguity sets. J. Sci. Comput. 94(1):12.Google Scholar
• Norkin VI, Pflug GC, Ruszczyński A (1998) A branch and bound method for stochastic global optimization. Math. Programming 83(1):425–450.Google Scholar
• Norton MD, Royset JO (2023) Diametrical risk minimization: Theory and computations. Machine Learn. 112(8):1–19.Google Scholar
• Pflug GC, Pichler A (2014) Multistage Stochastic Optimization, vol. 1104 (Springer, Cham, Switzerland).Google Scholar
• Pichler A, Xu H (2022) Quantitative stability analysis for minimax distributionally robust risk optimization. Math. Programming 191(1):47–77.Google Scholar
• Postek K, Ben-Tal A, Den Hertog D, Melenberg B (2018) Robust optimization with ambiguous stochastic constraints under mean and dispersion information. Oper. Res. 66(3):814–833.Link, Google Scholar
• Postek K, Romeijnders W, Den Hertog D, van der Vlerk MH (2019) An approximation framework for two-stage ambiguous stochastic integer programs under mean-mad information. Eur. J. Oper. Res. 274(2):432–444.Google Scholar
• Rahimian H, Mehrotra S (2022) Frameworks and results in distributionally robust optimization. Open J. Math. Optim. 3:1–85.Google Scholar
• Rockafellar RT, Uryasev S (2000) Optimization of conditional value-at-risk. J. Oper. Res. 2:21–42.Google Scholar
• Römisch W (2003) Stability of stochastic programming problems. Handbooks Oper. Res. Management Sci. 10:483–554.Google Scholar
• Scarf H (1959) Bayes solutions of the statistical inventory problem. Ann. Math. Statist. 30(2):490–508.Google Scholar
• Shapiro A (1994) Quantitative stability in stochastic programming. Math. Programming 67(1):99–108.Google Scholar
• Shapiro A, Dentcheva D, Ruszczyński A (2014) Lectures on Stochastic Programming: Modeling and Theory, 2nd ed (SIAM, Philadelphia).Google Scholar
• Shehadeh KS, Tucker EL (2022) Stochastic optimization models for location and inventory prepositioning of disaster relief supplies. Transportation Res. Part C Emerging Tech. 144:103871.Google Scholar
• Smith JE, Winkler RL (2006) The optimizer’s curse: Skepticism and postdecision surprise in decision analysis. Management Sci. 52(3):311–322.Link, Google Scholar
• So AMC (2011) Moment inequalities for sums of random matrices and their applications in optimization. Math. Programming 130(1):125–151.Google Scholar
• Sun H, Xu H (2016) Convergence analysis for distributionally robust optimization and equilibrium problems. Math. Oper. Res. 41(2):377–401.Link, Google Scholar
• Sun H, Zhang D, Wu SY, Chen L (2022) A modified exchange algorithm for distributional robust optimization and applications in risk management. Internat. Trans. Oper. Res. 29(1):130–157.Google Scholar
• Van Parys BP, Goulart PJ, Kuhn D (2016) Generalized Gauss inequalities via semidefinite programming. Math. Programming 156(1–2):271–302.Google Scholar
• Van Parys BP, Mohajerin Esfahani P, Kuhn D (2021) From data to decisions: Distributionally robust optimization is optimal. Management Sci. 67(6):3387–3402.Link, Google Scholar
• Villani C (2009) Optimal Transport: Old and New, vol. 338 (Springer, Berlin, Heidelberg).Google Scholar
• Wainwright MJ (2019) High-Dimensional Statistics: A Non-Asymptotic Viewpoint, vol. 48 (Cambridge University Press, Cambridge, UK).Google Scholar
• Wang J, Gao R, Xie Y (2021) Sinkhorn distributionally robust optimization. Preprint, submitted September 24, https://arxiv.org/abs/2109.11926.Google Scholar
• Wang S, Wang H, Honorio J (2023) Learning against distributional uncertainty: On the trade-off between robustness and specificity. Preprint, submitted January 31, https://arxiv.org/abs/2301.13565.Google Scholar
• Wiesemann W, Kuhn D, Sim M (2014) Distributionally robust convex optimization. Oper. Res. 62(6):1358–1376.Link, Google Scholar
• Xie W (2021) On distributionally robust chance constrained programs with Wasserstein distance. Math. Programming 186(1–2):115–155.Google Scholar
• Xu H, Liu Y, Sun H (2018) Distributionally robust optimization with matrix moment constraints: Lagrange duality and cutting plane methods. Math. Programming 169(2):489–529.Google Scholar
• Yam SCP, Yang H, Yuen FL (2016) Optimal asset allocation: Risk and information uncertainty. Eur. J. Oper. Res. 251(2):554–561.Google Scholar
• Zhang J, Xu H, Zhang L (2016) Quantitative stability analysis for distributionally robust optimization with moment constraints. SIAM J. Optim. 26(3):1855–1882.Google Scholar
• Zhao C, Guan Y (2015) Data-driven risk-averse two-stage stochastic program with ζ-structure probability metrics. Preprint, submitted July 19, https://optimization-online.org/?p=13523.Google Scholar