arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1406.6601math.NAcs.NA
收藏

缩放梯度投影方法的新收敛结果

New convergence results for the scaled gradient projection method

Università di Modena e Reggio Emilia(摩德纳和雷焦艾米利亚大学)

Silvia Bonettini, Marco Prato

AI总结:

本文研究缩放梯度投影方法的收敛性,证明在特定条件下序列收敛于极小点,并推导了O(1/k)的收敛速率。

摘要:

本文旨在深入分析缩放梯度投影(SGP)方法的收敛性,该方法由Bonettini等人提出用于约束光滑优化问题。SGP的主要特点是存在一个变量缩放矩阵乘以梯度,该矩阵可能在每次迭代中变化。尽管数值结果非常可靠,但仅提供了一个弱但通用的收敛定理,表明SGP生成序列的任何极限点都是驻点。在此,假设目标函数是凸的且存在解,证明在缩放矩阵序列满足简单且可实现的条件下,SGP生成的序列收敛于极小点。此外,假设目标函数的梯度是Lipschitz连续的,我们还能证明关于目标函数值的O(1/k)收敛速率。最后,我们展示了在相关图像恢复问题上的数值实验结果,证明所提出的缩放矩阵选择规则在计算方面也表现良好。

英文摘要:

The aim of this paper is to deepen the convergence analysis of the scaled gradient projection (SGP) method, proposed by Bonettini et al. in a recent paper for constrained smooth optimization. The main feature of SGP is the presence of a variable scaling matrix multiplying the gradient, which may change at each iteration. In the last few years, an extensive numerical experimentation showed that SGP equipped with a suitable choice of the scaling matrix is a very effective tool for solving large scale variational problems arising in image and signal processing. In spite of the very reliable numerical results observed, only a weak, though very general, convergence theorem is provided, establishing that any limit point of the sequence generated by SGP is stationary. Here, under the only assumption that the objective function is convex and that a solution exists, we prove that the sequence generated by SGP converges to a minimum point, if the scaling matrices sequence satisfies a simple and implementable condition. Moreover, assuming that the gradient of the objective function is Lipschitz continuous, we are also able to prove the O(1/k) convergence rate with respect to the objective function values. Finally, we present the results of a numerical experience on some relevant image restoration problems, showing that the proposed scaling matrix selection rule performs well also from the computational point of view.

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。

↑