arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2009.02740math.OC
收藏

约束分布随机最优化对偶平均算法的渐近性质

Asymptotic properties of dual averaging algorithm for constrained distributed stochastic optimization

Shengchao Zhao, Xing-Min Chen, Yongchao Liu

摘要:

考虑时变随机网络上的约束随机最优化问题,其中智能体在一个共同的约束集下共同最小化目标函数之和.与现有的分布式对偶平均算法主要研究其非渐近性质不同,本文不仅证明了算法的几乎必然收敛和几乎必然收敛的速度,而且证明了算法的渐近正态性和渐近有效性。首先,对于分布在随机网络上的一般约束凸优化问题,证明了可以实现几乎必然一致性,且各智能体的估计收敛于同一最优点。对于线性约束凸优化问题,我们证明了平均对偶序列的镜像映射以概率1识别最优解的积极约束,这有助于我们证明算法的几乎必然收敛率,进而建立算法的渐近正态性.此外,我们还证明了该算法是渐近最优的。据我们所知,这似乎是约束分布优化算法的第一个渐近正态性结果。最后,通过数值算例验证了理论分析的正确性.

英文摘要:

Considering the constrained stochastic optimization problem over a time-varying random network, where the agents are to collectively minimize a sum of objective functions subject to a common constraint set, we investigate asymptotic properties of a distributed algorithm based on dual averaging of gradients. Different from most existing works on distributed dual averaging algorithms that mainly concentrating on their non-asymptotic properties, we not only prove almost sure convergence and the rate of almost sure convergence, but also asymptotic normality and asymptotic efficiency of the algorithm. Firstly, for general constrained convex optimization problem distributed over a random network, we prove that almost sure consensus can be archived and the estimates of agents converge to the same optimal point. For the case of linear constrained convex optimization, we show that the mirror map of the averaged dual sequence identifies the active constraints of the optimal solution with probability 1, which helps us to prove the almost sure convergence rate and then establish asymptotic normality of the algorithm. Furthermore, we also verify that the algorithm is asymptotically optimal. To the best of our knowledge, it seems to be the first asymptotic normality result for constrained distributed optimization algorithms. Finally, a numerical example is provided to justify the theoretical analysis.

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。

↑