论文标题
随机多块ADMM：QP案例的基于ALM的视图
Random multi-block ADMM: an ALM based view for the QP case
论文作者
论文摘要
将随机过程嵌入乘数的交替方向方法（ADMM）最近引起了人们越来越多的兴趣，以解决以下事实：ADMM的直接多块概括不一定是收敛的。即使在实践中，从理论的角度来看，这种技术的引入可以\ textit {缓解} ADMM多块扩展的分歧，它也可以确保\ textit {contrygence in Experionation}，这可能不是其可靠性和效率的良好指标。在这项工作中，分析强烈凸的二次编程案例，我们解释了多块ADMM在不精确的增强Lagrangian方法的上下文中执行的块高斯seidel扫描。使用拟议的分析，我们能够概述文献中存在的替代技术，这些技术得到了更强的理论保证，能够确保ADMM方法的多块概括的收敛性。
Embedding randomization procedures in the Alternating Direction Method of Multipliers (ADMM) has recently attracted an increasing amount of interest as a remedy to the fact that the direct multi-block generalization of ADMM is not necessarily convergent. Even if, in practice, the introduction of such techniques could \textit{mitigate} the diverging behaviour of the multi-block extension of ADMM, from the theoretical point of view, it can ensure just the \textit{convergence in expectation}, which may not be a good indicator of its robustness and efficiency. In this work, analysing the strongly convex quadratic programming case, we interpret the block Gauss-Seidel sweep performed by the multi-block ADMM in the context of the inexact Augmented Lagrangian Method. Using the proposed analysis, we are able to outline an alternative technique to those present in literature which, supported from stronger theoretical guarantees, is able to ensure the convergence of the multi-block generalization of the ADMM method.
