Combating Conservativeness in Data-Driven Optimization under Uncertainty: A Solution Path Approach

In data-driven optimization, solution feasibility is often ensured through a "safe" reformulation of the uncertain constraints, such that an obtained data-driven solution is guaranteed to be feasible for the oracle formulation with high statistical confidence. Such approaches generally involve an implicit estimation of the whole feasible set that can scale rapidly with the problem dimension, in turn leading to over-conservative solutions. In this paper, we investigate a validation-based strategy to avoid set estimation by exploiting the intrinsic low dimensionality among all possible solutions output from a given reformulation. We demonstrate how our obtained solutions satisfy statistical feasibility guarantees with light dimension dependence, and how they are asymptotically optimal and thus regarded as the least conservative with respect to the considered reformulation classes. We apply this strategy to several data-driven optimization paradigms including (distributionally) robust optimization, sample average approximation and scenario optimization. Numerical experiments show encouraging performances of our strategy compared to established benchmarks.

[1]  Ruiwei Jiang,et al.  Data-driven chance constrained stochastic program , 2015, Mathematical Programming.

[2]  Marco C. Campi,et al.  The Exact Feasibility of Randomized Solutions of Uncertain Convex Programs , 2008, SIAM J. Optim..

[3]  L. Jeff Hong,et al.  Learning-Based Robust Optimization: Procedures and Statistical Guarantees , 2017, Manag. Sci..

[4]  R. Freund Postoptimal analysis of a linear program under simultaneous changes in matrix coefficients , 1985 .

[5]  Lorenzo Fagiano,et al.  Randomized Solutions to Convex Programs with Multiple Chance Constraints , 2012, SIAM J. Optim..

[6]  Henry Lam,et al.  Recovering Best Statistical Guarantees via the Empirical Divergence-Based Distributionally Robust Optimization , 2016, Oper. Res..

[7]  Mirjam Dür,et al.  Genericity Results in Linear Conic Programming - A Tour d'Horizon , 2017, Math. Oper. Res..

[8]  Laurent El Ghaoui,et al.  Robust Optimization , 2021, ICORES.

[9]  Marco C. Campi,et al.  Wait-and-judge scenario optimization , 2016, Mathematical Programming.

[10]  Ian R. Petersen,et al.  Minimax optimal control of stochastic uncertain systems with relative entropy constraints , 2000, IEEE Trans. Autom. Control..

[11]  Wei Wang,et al.  Sample average approximation of expected value constrained stochastic programs , 2008, Oper. Res. Lett..

[12]  Massimiliano Pontil,et al.  Empirical Bernstein Bounds and Sample-Variance Penalization , 2009, COLT.

[13]  W. Hoeffding Probability Inequalities for sums of Bounded Random Variables , 1963 .

[14]  Vishal Gupta,et al.  Data-driven robust optimization , 2013, Math. Program..

[15]  Liva Ralaivola,et al.  Empirical Bernstein Inequalities for U-Statistics , 2010, NIPS.

[16]  Bertrand Melenberg,et al.  Extending the Scope of Robust Quadratic Optimization , 2017, INFORMS J. Comput..

[17]  Jun-ya Gotoh,et al.  Robust Empirical Optimization is Almost the Same As Mean-Variance Optimization , 2015 .

[18]  Zhaolin Hu,et al.  Kullback-Leibler divergence constrained distributionally robust optimization , 2012 .

[19]  Alexander Shapiro,et al.  Convex Approximations of Chance Constrained Programs , 2006, SIAM J. Optim..

[20]  Güzin Bayraksan,et al.  Data-Driven Stochastic Programming Using Phi-Divergences , 2015 .

[21]  A. Kleywegt,et al.  Distributionally Robust Stochastic Optimization with Wasserstein Distance , 2016, Math. Oper. Res..

[22]  Henry Lam,et al.  Robust Sensitivity Analysis for Stochastic Systems , 2013, Math. Oper. Res..

[23]  Kengo Kato,et al.  Central limit theorems and bootstrap in high dimensions , 2014, 1412.3661.

[24]  Yang Kang,et al.  Sample Out-of-Sample Inference Based on Wasserstein Distance , 2016, Oper. Res..

[25]  M. KarthyekRajhaaA.,et al.  Robust Wasserstein profile inference and applications to machine learning , 2019, J. Appl. Probab..

[26]  Paul Glasserman,et al.  Robust risk measurement and model risk , 2014 .

[27]  Henry Lam,et al.  The empirical likelihood approach to quantifying uncertainty in sample average approximation , 2017, Oper. Res. Lett..

[28]  Jon A. Wellner,et al.  Weak Convergence and Empirical Processes: With Applications to Statistics , 1996 .

[29]  Daniel Kuhn,et al.  Data-driven distributionally robust optimization using the Wasserstein metric: performance guarantees and tractable reformulations , 2015, Mathematical Programming.

[30]  M. C. CAMPI,et al.  Random Convex Programs with L1-Regularization: Sparsity and Generalization , 2013, SIAM J. Control. Optim..

[31]  Yannis Pantazis,et al.  Path-Space Information Bounds for Uncertainty Quantification and Sensitivity Analysis of Stochastic Dynamics , 2015, SIAM/ASA J. Uncertain. Quantification.

[32]  A. Guillin,et al.  On the rate of convergence in Wasserstein distance of the empirical measure , 2013, 1312.2128.

[33]  Cynthia Rudin,et al.  Robust Optimization using Machine Learning for Uncertainty Sets , 2014, ISAIM.

[34]  Weijun Xie,et al.  On distributionally robust chance constrained programs with Wasserstein distance , 2018, Mathematical Programming.

[35]  Marco C. Campi,et al.  FAST - Fast Algorithm for the Scenario Technique , 2014, Oper. Res..

[36]  Andrew E. B. Lim,et al.  Robust Empirical Optimization is Almost the Same As Mean-Variance Optimization , 2015, Oper. Res. Lett..

[37]  Daniel Kuhn,et al.  A distributionally robust perspective on uncertainty quantification and chance constrained programming , 2015, Mathematical Programming.

[38]  Daniel Kuhn,et al.  Generalized Gauss inequalities via semidefinite programming , 2015, Mathematical Programming.

[39]  Shie Mannor,et al.  Optimization Under Probabilistic Envelope Constraints , 2012, Oper. Res..

[40]  Constantine Caramanis,et al.  Theory and Applications of Robust Optimization , 2010, SIAM Rev..

[41]  Gábor Lugosi,et al.  Concentration Inequalities - A Nonasymptotic Theory of Independence , 2013, Concentration Inequalities.

[42]  Melvyn Sim,et al.  Distributionally Robust Optimization and Its Tractable Approximations , 2010, Oper. Res..

[43]  John Duchi,et al.  Statistics of Robust Optimization: A Generalized Empirical Likelihood Approach , 2016, Math. Oper. Res..

[44]  Donald Goldfarb,et al.  Robust Portfolio Selection Problems , 2003, Math. Oper. Res..

[45]  Laurent El Ghaoui,et al.  Worst-Case Value-At-Risk and Robust Portfolio Optimization: A Conic Programming Approach , 2003, Oper. Res..

[46]  M. Kosorok Introduction to Empirical Processes and Semiparametric Inference , 2008 .

[47]  Arkadi Nemirovski,et al.  Robust solutions of Linear Programming problems contaminated with uncertain data , 2000, Math. Program..

[48]  P. Glasserman,et al.  Robust risk measurement and model risk , 2012 .

[49]  Alexander Shapiro,et al.  Lectures on Stochastic Programming: Modeling and Theory , 2009 .

[50]  Shane G. Henderson,et al.  Call Center Staffing with Simulation and Cutting Plane Methods , 2004, Ann. Oper. Res..

[51]  Vishal Gupta,et al.  Near-Optimal Bayesian Ambiguity Sets for Distributionally Robust Optimization , 2019, Manag. Sci..

[52]  D. Hunter Portfolio optimization with conditional value-at-risk objective and constraints , 2002 .

[53]  Daniel Kuhn,et al.  Distributionally Robust Convex Optimization , 2014, Oper. Res..

[54]  Melvyn Sim,et al.  Incorporating Asymmetric Distributional Information in Robust Value-at-Risk Optimization , 2008, Manag. Sci..

[55]  Yinyu Ye,et al.  Distributionally Robust Optimization Under Moment Uncertainty with Application to Data-Driven Problems , 2010, Oper. Res..

[56]  Roman Vershynin,et al.  Introduction to the non-asymptotic analysis of random matrices , 2010, Compressed Sensing.

[57]  Giuseppe Carlo Calafiore,et al.  Uncertain convex programs: randomized solutions and confidence levels , 2005, Math. Program..

[58]  A. Nemirovski On tractable approximations of randomly perturbed convex constraints , 2003, 42nd IEEE International Conference on Decision and Control (IEEE Cat. No.03CH37475).

[59]  Henry Lam,et al.  Sensitivity to Serial Dependency of Input Processes: A Robust Approach , 2016, Manag. Sci..

[60]  Anja De Waegenaere,et al.  Robust Solutions of Optimization Problems Affected by Uncertain Probabilities , 2011, Manag. Sci..

[61]  Marco C. Campi,et al.  A Sampling-and-Discarding Approach to Chance-Constrained Optimization: Feasibility and Optimality , 2011, J. Optim. Theory Appl..

[62]  Karthyek R. A. Murthy,et al.  Quantifying Distributional Model Risk Via Optimal Transport , 2016, Math. Oper. Res..

[63]  Xiaobo Li,et al.  Robustness to Dependency in Portfolio Optimization Using Overlapping Marginals , 2015, Oper. Res..