Multistep stochastic mirror descent for risk-averse convex stochastic programs based on extended polyhedral risk measures

We consider risk-averse convex stochastic programs expressed in terms of extended polyhedral risk measures. We derive computable confidence intervals on the optimal value of such stochastic programs using the Robust Stochastic Approximation and the Stochastic Mirror Descent (SMD) algorithms. When the objective functions are uniformly convex, we also propose a multistep extension of the Stochastic Mirror Descent algorithm and obtain confidence intervals on both the optimal values and optimal solutions. Numerical simulations show that our confidence intervals are much less conservative and are quicker to compute than previously obtained confidence intervals for SMD and that the multistep Stochastic Mirror Descent algorithm can obtain a good approximate solution much quicker than its nonmultistep counterpart.

[1]  Boris Polyak,et al.  Acceleration of stochastic approximation by averaging , 1992 .

[2]  D. Morton,et al.  Assessing policy quality in multi-stage stochastic programming , 2004 .

[3]  Ohad Shamir,et al.  Making Gradient Descent Optimal for Strongly Convex Stochastic Optimization , 2011, ICML.

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

[5]  Georg Ch. Pflug,et al.  Asymptotic distribution of law-invariant risk functionals , 2010, Finance Stochastics.

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

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

[8]  Philippe Artzner,et al.  Coherent Measures of Risk , 1999 .

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

[10]  Alexander Shapiro,et al.  Lectures on Stochastic Programming - Modeling and Theory, Second Edition , 2014, MOS-SIAM Series on Optimization.

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

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

[13]  M. V. F. Pereira,et al.  Multi-stage stochastic optimization applied to energy planning , 1991, Math. Program..

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

[15]  Werner Römisch,et al.  Delta Method, Infinite Dimensional , 2006 .

[16]  Rüdiger Schultz,et al.  Strong convexity in stochastic programs with complete recourse , 1994 .

[17]  Angelia Nedic,et al.  On Stochastic Subgradient Mirror-Descent Algorithm with Weighted Averaging , 2013, SIAM J. Optim..

[18]  A. Shapiro,et al.  The Sample Average Approximation Method for Stochastic Programs with Integer Recourse , 2002 .

[19]  Werner Römisch,et al.  Polyhedral Risk Measures in Stochastic Programming , 2005, SIAM J. Optim..

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

[21]  M. Talagrand.  The Glivenko-Cantelli Problem , 1987 .

[22]  M. Talagrand.  The Glivenko-Cantelli problem, ten years later , 1996 .

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

[24]  Werner Römisch,et al.  Stochastic Integer Programming: Limit Theorems and Confidence Intervals , 2005, Math. Oper. Res..

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

[26]  Alexander Shapiro,et al.  On the Rate of Convergence of Optimal Solutions of Monte Carlo Approximations of Stochastic Programs , 2000, SIAM J. Optim..

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

[28]  M. Puri,et al.  Testing hypotheses about the equality of several risk measure values with applications in insurance , 2006 .

[29]  David P. Morton,et al.  A Sequential Sampling Procedure for Stochastic Programming , 2011, Oper. Res..

[30]  Güzin Bayraksan,et al.  Fixed-Width Sequential Stopping Rules for a Class of Stochastic Programs , 2012, SIAM J. Optim..

[31]  Arkadi Nemirovski,et al.  Non-asymptotic confidence bounds for the optimal value of a stochastic program , 2016, Optim. Methods Softw..

[32]  M. Talagrand.  Sharper Bounds for Gaussian and Empirical Processes , 1994 .

[33]  Vincent Guigues.  Convergence Analysis of Sampling-Based Decomposition Methods for Risk-Averse Multistage Stochastic Convex Programs , 2016, SIAM J. Optim..

[34]  Werner Römisch,et al.  Stability of Solutions for Stochastic Programs with Complete Recourse , 1993, Math. Oper. Res..

[35]  A. Shapiro.  Asymptotic Properties of Statistical Estimators in Stochastic Programming , 1989 .

[36]  Y. Nesterov,et al.  Primal-dual subgradient methods for minimizing uniformly convex functions , 2010, 1401.1792.

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

[38]  David P. Morton,et al.  Assessing solution quality in stochastic programs , 2006, Algorithms for Optimization with Incomplete Information.

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

[40]  Bruce D. Spencer,et al.  The Delta Method , 1980 .

[41]  Werner Römisch,et al.  Sampling-Based Decomposition Methods for Multistage Stochastic Programs Based on Extended Polyhedral Risk Measures , 2012, SIAM J. Optim..

[42]  Saeed Ghadimi,et al.  Optimal Stochastic Approximation Algorithms for Strongly Convex Stochastic Composite Optimization I: A Generic Algorithmic Framework , 2012, SIAM J. Optim..