期刊
SIAM JOURNAL ON IMAGING SCIENCES
卷 7, 期 2, 页码 1388-1419出版社
SIAM PUBLICATIONS
DOI: 10.1137/130942954
关键词
nonconvex optimization; Heavy-ball method; inertial forward-backward splitting; Kurdyka-Lojasiewicz inequality; proof of convergence
类别
资金
- German Research Foundation (DFG) [BR 3815/5-1]
- Austrian science fund (FWF) under the START project BIVISION [Y729]
In this paper we study an algorithm for solving a minimization problem composed of a differentiable (possibly nonconvex) and a convex (possibly nondifferentiable) function. The algorithm iPiano combines forward-backward splitting with an inertial force. It can be seen as a nonsmooth split version of the Heavy-ball method from Polyak. A rigorous analysis of the algorithm for the proposed class of problems yields global convergence of the function values and the arguments. This makes the algorithm robust for usage on nonconvex problems. The convergence result is obtained based on the Kurdyka-Lojasiewicz inequality. This is a very weak restriction, which was used to prove convergence for several other gradient methods. First, an abstract convergence theorem for a generic algorithm is proved, and then iPiano is shown to satisfy the requirements of this theorem. Furthermore, a convergence rate is established for the general problem class. We demonstrate iPiano on computer vision problems-image denoising with learned priors and diffusion based image compression.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据