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 2204.09416cs.ITmath.IT
收藏

相位恢复问题全局几何景观的近似最优界

Nearly optimal bounds for the global geometric landscape of phase retrieval

Jian-Feng Cai, Meng Huang, Dong Li, Yang Wang

AI总结:

本文证明仅需 $m=O(n \log n)$ 次高斯随机测量,即可高概率保证相位恢复问题常用估计量损失函数具有所有局部极小化器均为全局的良性几何景观,推进了 Sun-Qu-Wright 提出的开放问题。

摘要:

相位恢复问题关注从一组仅包含幅值的测量值 $y_j=|\langle \bf{a}_j,\bf{x} \rangle|, \\; j=1,\ldots,m$ 中恢复未知信号 $\bf{x} \in \mathbb{R}^n$。一种自然的最小二乘公式可用于高效解决此问题,即使采用随机初始化,尽管其损失函数具有非凸性。解释这一令人惊讶现象的一种方式是良性的几何景观:(1) 所有局部极小化器都是全局的;以及 (2) 目标函数在每个鞍点和局部极大化器周围具有负曲率。在本文中,我们证明 $m=O(n \log n)$ 次高斯随机测量足以保证常用估计量的损失函数以高概率具有这种良性的几何景观。这是朝着解决 Sun-Qu-Wright 提出的开放问题迈出的一步,他们提出 $O(n \log n)$ 甚至 $O(n)$ 就足以保证有利的几何性质。

英文摘要:

The phase retrieval problem is concerned with recovering an unknown signal $\bf{x} \in \mathbb{R}^n$ from a set of magnitude-only measurements $y_j=|\langle \bf{a}_j,\bf{x} \rangle|, \; j=1,\ldots,m$. A natural least squares formulation can be used to solve this problem efficiently even with random initialization, despite its non-convexity of the loss function. One way to explain this surprising phenomenon is the benign geometric landscape: (1) all local minimizers are global; and (2) the objective function has a negative curvature around each saddle point and local maximizer. In this paper, we show that $m=O(n \log n)$ Gaussian random measurements are sufficient to guarantee the loss function of a commonly used estimator has such benign geometric landscape with high probability. This is a step toward answering the open problem given by Sun-Qu-Wright, in which the authors suggest that $O(n \log n)$ or even $O(n)$ is enough to guarantee the favorable geometric property.

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。

↑