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 1801.03013math.OC
收藏

基于非凸拉格朗日的Optimization:监控方案和整体收敛

Nonconvex Lagrangian-Based Optimization: Monitoring Schemes and Global Convergence

Jérôme Bolte, Shoham Sabach, Marc Teboulle

摘要:

我们介绍了一种新的方法,解决全球分析一类困难的非凸非光滑最优化问题的重要框架内的拉格朗日为基础的方法。这个真正的非线性类捕捉到了现代不同应用领域中的许多问题。它具有复杂的几何形状,资格条件和其他规律性属性并不处处成立。为了解决这些问题,我们沿着几条研究路线,开发一个原始的一般拉格朗日方法,可以处理,所有一次,与上述障碍。我们的方法的第一个创新特点是引入拉格朗日序列的概念,广泛的一类算法。这种方法的核心是将任意下降法转化为乘子法的思想。其次,我们提供了这些方法与过渡制度,使我们能够确定在许多步骤的区域,我们可以调整的步长的算法的最终收敛制度。然后,尽管最小-最大性质的拉格朗日方法,使用原始的李雅普诺夫方法,我们证明了每个有界序列所产生的监测计划是全局收敛到一个临界点的一些基本的拉格朗日为基础的方法在广泛的半代数设置,这是我们所知的,是第一次这种。

英文摘要:

We introduce a novel approach addressing global analysis of a difficult class of nonconvex-nonsmooth optimization problems within the important framework of Lagrangian-based methods. This genuine nonlinear class captures many problems in modern disparate fields of applications. It features complex geometries, qualification conditions, and other regularity properties do not hold everywhere. To address these issues we work along several research lines to develop an original general Lagrangian methodology which can deal, all at once, with the above obstacles. A first innovative feature of our approach is to introduce the concept of Lagrangian sequences for a broad class of algorithms. Central to this methodology is the idea of turning an arbitrary descent method into a multiplier method. Secondly, we provide these methods with a transitional regime allowing us to identify in finitely many steps a zone where we can tune the step-sizes of the algorithm for the final converging regime. Then, despite the min-max nature of Lagrangian methods, using an original Lyapunov method we prove that each bounded sequence generated by the resulting monitoring schemes are globally convergent to a critical point for some fundamental Lagrangian-based methods in the broad semialgebraic setting, which to the best of our knowledge, are the first of this kind.

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。

↑