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 1605.03791math.NAcs.NA
收藏

关于非凸优化中基于线搜索的近端梯度方法收敛性的研究

On the convergence of a linesearch based proximal-gradient method for nonconvex optimization

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

Silvia Bonettini, Ignace Loris, Federica Porta, Marco Prato, Simone Rebegoldi

AI总结:

本文研究了一种基于变量度量线搜索的近端梯度方法,证明在目标函数满足Kurdyka-Lojasiewicz性质时,该算法能收敛到临界点,并在图像处理中验证了其灵活性和鲁棒性。

摘要:

我们考虑了一种基于变量度量线搜索的近端梯度方法,用于最小化一个光滑可能非凸函数与一个凸可能非光滑项之和。我们证明,如果目标函数在其定义域的每个点上满足Kurdyka-Lojasiewicz性质,并且假设存在极限点,则该迭代算法能收敛到临界点。所提出的方法被应用于广泛的图像处理问题,数值测试显示该算法在与最近提出的其他方法相比时,表现出灵活性、鲁棒性和竞争力。

英文摘要:

We consider a variable metric linesearch based proximal gradient method for the minimization of the sum of a smooth, possibly nonconvex function plus a convex, possibly nonsmooth term. We prove convergence of this iterative algorithm to a critical point if the objective function satisfies the Kurdyka-Lojasiewicz property at each point of its domain, under the assumption that a limit point exists. The proposed method is applied to a wide collection of image processing problems and our numerical tests show that our algorithm results to be flexible, robust and competitive when compared to recently proposed approaches able to address the optimization problems arising in the considered applications.

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。

↑