In this paper, we study a general low-rank matrix recovery problem with linear measurements corrupted by some noise. The objective is to understand under what conditions on the restricted isometry property (RIP) of the problem local search methods can find the ground truth with a small error. By analyzing the landscape of the non-convex problem, we first propose a global guarantee on the maximum distance between an arbitrary local minimizer and the ground truth under the assumption that the RIP constant is smaller than $1/2$. We show that this distance shrinks to zero as the intensity of the noise reduces. Our new guarantee is sharp in terms of the RIP constant and is much stronger than the existing results. We then present a local guarantee for problems with an arbitrary RIP constant, which states that any local minimizer is either considerably close to the ground truth or far away from it. Next, we prove the strict saddle property, which guarantees the global convergence of the perturbed gradient descent method in polynomial time. The developed results demonstrate how the noise intensity and the RIP constant of the problem affect the landscape of the problem.
翻译:在本文中,我们研究的是一般的低级矩阵回收问题,即线性测量被一些噪音腐蚀。目的是了解在什么条件下,当地搜索方法能够用一个小错误找到问题限量的等量属性(RIP)的地面真相。通过分析非康韦克斯问题的地貌,我们首先提出一种全球保证,即任意的当地最小化者与地面真相之间的最大距离,假设RIP常数小于1/2美元。我们表明,随着噪音的强度的降低,这种距离会缩小到零。我们的新保证在RIP常数方面是尖锐的,比现有结果要强得多。我们随后对任意的RIP常数的问题提出当地保证,指出任何当地的最小化者要么与地面真相相当,要么离它很远。接下来,我们证明了严格的挂载财产,这保证了在多瑙河时间受扰动的梯层下法的全球趋同。我们得出的结果表明,噪音强度和问题的RIP常数是如何影响问题全局的。