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 1703.09477math.OCstat.ML
收藏

前向-后向算法的收敛性:借助几何超越最坏情形

Convergence of the Forward-Backward Algorithm: Beyond the Worst Case with the Help of Geometry

Guillaume Garrigos, Lorenzo Rosasco, Silvia Villa

AI总结:

本文在任意集合上重新审视几何条件,全面研究前向-后向算法的收敛性,提出无限维凸最小化的首个Łojasiewicz不等式及低复杂度先验逆问题的新线性速率,并建立几何与先验条件的联系。

摘要:

我们提供了在前向-后向算法在适当几何条件(如条件数或Łojasiewicz性质)下收敛性的全面研究。这些几何概念通常本质上是局部的,可能无法描述在逆问题和信号处理中相关的目标函数的精细几何,这些函数在流形上或相对于弱拓扑开放集合上具有良好的行为。受此观察启发,我们在任意集合上重新审视这些几何概念。这反过来使我们能够呈现若干新结果,并以统一视角汇集文献中分散的各种结果。我们的贡献包括对无限维凸最小化问题的分析,展示了与紧算子相关的二次函数的首个Łojasiewicz不等式,以及为具有低复杂度先验的逆问题推导出新的线性收敛速率。我们的方法能够在逆问题中的几何与先验条件(如源条件或受限等距性质)之间建立意想不到的联系。

英文摘要:

We provide a comprehensive study of the convergence of the forward-backward algorithm under suitable geometric conditions, such as conditioning or Łojasiewicz properties. These geometrical notions are usually local by nature, and may fail to describe the fine geometry of objective functions relevant in inverse problems and signal processing, that have a nice behaviour on manifolds, or sets open with respect to a weak topology. Motivated by this observation, we revisit those geometric notions over arbitrary sets. In turn, this allows us to present several new results as well as collect in a unified view a variety of results scattered in the literature. Our contributions include the analysis of infinite dimensional convex minimization problems, showing the first Łojasiewicz inequality for a quadratic function associated to a compact operator, and the derivation of new linear rates for problems arising from inverse problems with low-complexity priors. Our approach allows to establish unexpected connections between geometry and a priori conditions in inverse problems, such as source conditions, or restricted isometry properties.

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。

↑