Non-asymptotic confidence bounds for the optimal value of a stochastic program

We discuss a general approach to building non-asymptotic confidence bounds for Stochastic Optimization problems. Our principal contribution is the observation that a Sample Average Approximation of a problem supplies upper and lower bounds for the optimal value of the problem which are essentially better than the quality of the corresponding optimal solutions. At the same time, such bounds are more reliable than ‘standard’ confidence bounds obtained through the asymptotic approach. We also discuss bounding the optimal value of MinMax Stochastic Optimization and stochastically constrained problems. We conclude with a simulation study illustrating the numerical behaviour of the proposed bounds.

[1]  John Darzentas,et al.  Problem Complexity and Method Efficiency in Optimization , 1983 .

[2]  J. Dupacová,et al.  ASYMPTOTIC BEHAVIOR OF STATISTICAL ESTIMATORS AND OF OPTIMAL SOLUTIONS OF STOCHASTIC OPTIMIZATION PROBLEMS , 1988 .

[3]  Alexander Shapiro,et al.  Asymptotic analysis of stochastic programs , 1991, Ann. Oper. Res..

[4]  R. Tyrrell Rockafellar,et al.  Asymptotic Theory for Solutions in Statistical Estimation and Stochastic Programming , 1993, Math. Oper. Res..

[5]  Georg Ch. Pflug,et al.  Asymptotic Stochastic Programs , 1995, Math. Oper. Res..

[6]  Roger J.-B. Wets,et al.  Probabilistic bounds (via large deviations) for the solutions of stochastic programming problems , 1995, Ann. Oper. Res..

[7]  Georg Ch. Pflug,et al.  Stochastic programs and statistical data , 1999, Ann. Oper. Res..

[8]  David P. Morton,et al.  Monte Carlo bounding techniques for determining solution quality in stochastic programs , 1999, Oper. Res. Lett..

[9]  R. Rockafellar,et al.  Conditional Value-at-Risk for General Loss Distributions , 2001 .

[10]  Alexander Shapiro,et al.  The Sample Average Approximation Method for Stochastic Discrete Optimization , 2002, SIAM J. Optim..

[11]  A. Shapiro.  Monte Carlo Sampling Methods , 2003 .

[12]  G. Pflug.  Stochastic Optimization and Statistical Inference , 2003 .

[13]  Alexander Shapiro,et al.  The Sample Average Approximation Method Applied to Stochastic Routing Problems: A Computational Study , 2003, Comput. Optim. Appl..

[14]  Alexander Shapiro,et al.  On Complexity of Stochastic Programming Problems , 2005 .

[15]  Alexander Shapiro,et al.  The empirical behavior of sampling methods for stochastic programming , 2006, Ann. Oper. Res..

[16]  H. Robbins.  A Stochastic Approximation Method , 1951 .

[17]  A. Juditsky,et al.  Large Deviations of Vector-valued Martingales in 2-Smooth Normed Spaces , 2008, 0809.0813.

[18]  Ohad Shamir,et al.  Learnability and Stability in the General Learning Setting , 2009, COLT.

[19]  Alexander Shapiro,et al.  Stochastic Approximation approach to Stochastic Programming , 2013 .

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

[21]  A. Juditsky,et al.  5 First-Order Methods for Nonsmooth Convex Large-Scale Optimization , I : General Purpose Methods , 2010 .

[22]  Léon Bottou,et al.  Large-Scale Machine Learning with Stochastic Gradient Descent , 2010, COMPSTAT.

[23]  Vianney Perchet,et al.  The multi-armed bandit problem with covariates , 2011, ArXiv.

[24]  S. Geer,et al.  The Bernstein–Orlicz norm and deviation inequalities , 2011, 1111.2450.

[25]  Alexander Shapiro,et al.  Validation analysis of mirror descent stochastic approximation method , 2012, Math. Program..

[26]  Andrew Cotter,et al.  Stochastic Optimization for Machine Learning , 2013, ArXiv.

[27]  Vianney Perchet,et al.  Bounded regret in stochastic multi-armed bandits , 2013, COLT.

[28]  Yurii Nesterov,et al.  On first-order algorithms for l1/nuclear norm minimization , 2013, Acta Numerica.

[29]  Alexander Shapiro,et al.  Stochastic Approximation approach to Stochastic Programming , 2013 .

[30]  Vincent Guigues,et al.  Multistep stochastic mirror descent for risk-averse convex stochastic programs based on extended polyhedral risk measures , 2014, Math. Program..

[31]  Naomi S. Altman,et al.  Quantile regression , 2019, Nature Methods.