arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2106.11577math.OCstat.ML
收藏

用随机增广拉格朗日型算法有效求解期望约束随机最优化

Solving Stochastic Optimization with Expectation Constraints Efficiently by a Stochastic Augmented Lagrangian-Type Algorithm

Liwei Zhang, Yule Zhang, Jia Wu, Xiantao Xiao

摘要:

本文考虑了具有不等式凸期望约束的凸期望函数的极小化问题。我们提出了一个可计算的随机逼近型算法,即随机线性化邻近乘子法,以解决这个凸随机最优化问题。该算法可以粗略地看作是随机逼近和传统的乘子逼近法的混合。在温和的条件下,我们表明,该算法表现出$O(K^{-1/2})$预期的收敛速度的目标减少和约束违反,如果在算法中的参数选择得当,其中$K$表示的迭代次数。此外,我们证明了,在很高的概率,该算法有$O(\log(K)K^{-1/2})$约束违反界和$O(\log^{3/2}(K)K^{-1/2})$的目标界。一些初步的数值结果表明所提出的算法的性能。

英文摘要:

This paper considers the problem of minimizing a convex expectation function with a set of inequality convex expectation constraints. We present a computable stochastic approximation type algorithm, namely the stochastic linearized proximal method of multipliers, to solve this convex stochastic optimization problem. This algorithm can be roughly viewed as a hybrid of stochastic approximation and the traditional proximal method of multipliers. Under mild conditions, we show that this algorithm exhibits $O(K^{-1/2})$ expected convergence rates for both objective reduction and constraint violation if parameters in the algorithm are properly chosen, where $K$ denotes the number of iterations. Moreover, we show that, with high probability, the algorithm has $O(\log(K)K^{-1/2})$ constraint violation bound and $O(\log^{3/2}(K)K^{-1/2})$ objective bound. Some preliminary numerical results demonstrate the performance of the proposed algorithm.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑