arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2105.08232math.OCcs.LGstat.ML
收藏

含受损测量值的低秩矩阵恢复问题的精确受限等距性质界

Sharp Restricted Isometry Property Bounds for Low-rank Matrix Recovery Problems with Corrupted Measurements

University of California, Berkeley(加利福尼亚大学伯克利分校)

Ziye Ma, Yingjie Bi, Javad Lavaei, Somayeh Sojoudi

AI总结:

该研究针对含噪声线性测量的低秩矩阵恢复问题,分析非凸问题景观,给出RIP常数小于1/2时的精确全局距离保证、任意RIP常数下的局部保证,还证明严格鞍点性质以保障扰动梯度下降多项式时间全局收敛。

摘要:

本文研究了一类存在噪声干扰的线性测量值下的通用低秩矩阵恢复问题。研究目标是明确当问题的受限等距性质(RIP)满足何种条件时,局部搜索方法能够以较小误差找到真实值。通过分析该非凸问题的解空间景观,我们首先在RIP常数小于$1/2$的假设下,提出了关于任意局部极小值点与真实值之间最大距离的全局保证。我们证明,随着噪声强度降低,该距离会收缩至零。我们的新保证在RIP常数方面是精确的,且远强于现有结果。随后,我们针对任意RIP常数的问题提出了局部保证,即任意局部极小值点要么与真实值相当接近,要么与之相距甚远。接着,我们证明了严格鞍点性质,该性质可保证带扰动的梯度下降法在多项式时间内实现全局收敛。所得结果揭示了问题的噪声强度与RIP常数如何影响问题的解空间景观。

英文摘要:

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.

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。

↑