arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1707.03324math.OCcs.CCcs.LGstat.ML
收藏

多阶段随机最优化的动态随机逼近

Dynamic Stochastic Approximation for Multi-stage Stochastic Optimization

H. Milton Stewart School of Industrial and Systems Engineering, Georgia Institute of Technology(佐治亚理工学院H. Milton Stewart工业与系统工程学院)

Guanghui Lan, Zhiqiang Zhou

摘要:

本文考虑了在每一阶段都具有凸目标和锥约束的多阶段随机最优化问题。我们提出了一种新的随机一阶方法,即动态随机逼近(DSA)算法,用于解决这类随机最优化问题。我们表明,DSA可以实现一个最佳的${\cal O}(1/ε^4)$收敛速率方面所需的情况下,应用到一个三阶段的随机最优化问题的总数。我们进一步表明,这种收敛速率可以提高到${\cal O}(1/ε^2)$时,目标函数是强凸的。我们还讨论了变形的DSA解决更一般的多阶段随机最优化问题的阶段数$T > 3$。所开发的DSA算法只需要通过一次场景树,以计算多阶段随机最优化问题的$ε$ -解决方案。因此,DSA所需的存储器仅相对于级数线性增长。据我们所知,这是第一次,随机逼近型方法推广到多阶段随机最优化与$T \ge 3$。

英文摘要:

In this paper, we consider multi-stage stochastic optimization problems with convex objectives and conic constraints at each stage. We present a new stochastic first-order method, namely the dynamic stochastic approximation (DSA) algorithm, for solving these types of stochastic optimization problems. We show that DSA can achieve an optimal ${\cal O}(1/ε^4)$ rate of convergence in terms of the total number of required scenarios when applied to a three-stage stochastic optimization problem. We further show that this rate of convergence can be improved to ${\cal O}(1/ε^2)$ when the objective function is strongly convex. We also discuss variants of DSA for solving more general multi-stage stochastic optimization problems with the number of stages $T > 3$. The developed DSA algorithms only need to go through the scenario tree once in order to compute an $ε$-solution of the multi-stage stochastic optimization problem. As a result, the memory required by DSA only grows linearly with respect to the number of stages. To the best of our knowledge, this is the first time that stochastic approximation type methods are generalized for multi-stage stochastic optimization with $T \ge 3$.

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。

↑