arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1712.04767cs.ITmath.IT
收藏

非光滑非凸优化的罚对偶分解方法

Penalty Dual Decomposition Method For Nonsmooth Nonconvex Optimization

Qingjiang Shi, Mingyi Hong, Xiao Fu, Tsung-Hui Chang

摘要:

许多当代信号处理、机器学习和无线通信应用都可以用非凸非光滑优化问题来表示。对于这类问题,尤其是当优化变量在非凸约束条件下非线性耦合时,往往缺乏有效的算法。在这项工作中,我们提出了一个算法命名为惩罚对偶分解(PDD),这些困难的问题,并讨论了它的各种应用。PDD是一个双循环迭代算法。它的内部迭代用于通过块坐标下降型方法不精确地解决非凸非光滑增广拉格朗日问题,而其外部迭代更新对偶变量和/或惩罚参数。在本工作的第一部分中,我们描述了PDD算法,并严格建立其收敛到KKT解决方案。在第二部分中,我们评估PDD的性能定制它的三个应用程序所产生的信号处理和无线通信。

英文摘要:

Many contemporary signal processing, machine learning and wireless communication applications can be formulated as nonconvex nonsmooth optimization problems. Often there is a lack of efficient algorithms for these problems, especially when the optimization variables are nonlinearly coupled in some nonconvex constraints. In this work, we propose an algorithm named penalty dual decomposition (PDD) for these difficult problems and discuss its various applications. The PDD is a double-loop iterative algorithm. Its inner iterations is used to inexactly solve a nonconvex nonsmooth augmented Lagrangian problem via block-coordinate-descenttype methods, while its outer iteration updates the dual variables and/or a penalty parameter. In Part I of this work, we describe the PDD algorithm and rigorously establish its convergence to KKT solutions. In Part II we evaluate the performance of PDD by customizing it to three applications arising from signal processing and wireless communications.

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。

↑