Convergence Analysis of Stationary Points in Sample Average Approximation of Stochastic Programs with Second Order Stochastic Dominance Constraints1 Dedicated to Professor Jon Borwein on the occasion of his 60th birthday

Sample average approximation (SAA) method which is also known under various names such as Monte Carlo method, sample path optimization and stochastic counterpart has recently been applied to solve stochastic programs with second order stochastic dominance (SSD) constraints. In particular, Hu et al [19] presented a detailed convergence analysis of ε-optimal values and optimal solutions of sample average approximated stochastic programs with polyhedral SSD constraints. In this paper, we complement the existing research by presenting convergence analysis of stationary points when SAA is applied to a class of stochastic minimization problems with SSD constraints. Specifically, under some moderate conditions we prove that optimal solutions and stationary points obtained from solving sample average approximated problems converge with probability one (w.p.1) to their true counterparts. Moreover, by exploiting some recent results on large deviation of random functions and sensitivity analysis of generalized equations, we derive exponential rate of convergence of stationary points.