中文摘要：

讨论了随机约束非光滑凸优化的基于空间分解的样本均值近似（SAA）方法．在适当的条件下，SAA问题的解以概率1收敛到其真实解，并且随着样本容量的增加，收敛速度是指数的．基于分解理论，给出了求解SAA问题的超线性收敛速度的算法框架．

英文摘要：

Sample average approximation （SAA） method based on space-decomposition method to solve stochastic constrained nonsmooth convex optimization is discussed. Under some moderate conditions, the SAA solution converges to its true counterpart with probability approaching one and convergence is exponential fast with the increase of sample size. Based on the decomposition theory, a superlinear convergent algorithm frame is designed to solve the SAA problem.