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 1602.06664cs.ITmath.ITmath.OCstat.ML
收藏

相位恢复的几何分析

A Geometric Analysis of Phase Retrieval

Ju Sun, Qing Qu, John Wright

摘要:

我们能从复信号的傅里叶幅度中恢复它吗?更一般地,给定一组$m$测量,对于$k = 1, \dots, m$的$y_k = |\mathbf a_k^* \mathbf x|$,有可能恢复$\mathbf x \in \mathbb{C}^n$(即,长度- $n$复合载体)?这种广义相位恢复(GPR)问题是各个学科的基本任务,并且一直是最近研究的主题。自然非凸算法在实际应用中对探地雷达有很好的效果,但缺乏明确的理论解释。在本文中,我们采取了一个步骤来弥合这一差距。我们证明了当测量向量$\mathbf a_k$是一般的(i.i.d.)复高斯)并且测量的数量足够大($m \ge C n \log^3 n$),则GPR的自然最小二乘公式具有以下良性几何结构:(1)不存在伪局部最小值,并且所有全局最小值等于目标信号$\mathbf x$,直到全局相位;以及(2)目标函数在每个鞍点周围具有负曲率。这种结构允许许多迭代优化方法有效地找到全局最小值,而无需特殊的初始化。为了证实这一说法,我们描述和分析了二阶信赖域算法。

英文摘要:

Can we recover a complex signal from its Fourier magnitudes? More generally, given a set of $m$ measurements, $y_k = |\mathbf a_k^* \mathbf x|$ for $k = 1, \dots, m$, is it possible to recover $\mathbf x \in \mathbb{C}^n$ (i.e., length-$n$ complex vector)? This **generalized phase retrieval** (GPR) problem is a fundamental task in various disciplines, and has been the subject of much recent investigation. Natural nonconvex heuristics often work remarkably well for GPR in practice, but lack clear theoretical explanations. In this paper, we take a step towards bridging this gap. We prove that when the measurement vectors $\mathbf a_k$'s are generic (i.i.d. complex Gaussian) and the number of measurements is large enough ($m \ge C n \log^3 n$), with high probability, a natural least-squares formulation for GPR has the following benign geometric structure: (1) there are no spurious local minimizers, and all global minimizers are equal to the target signal $\mathbf x$, up to a global phase; and (2) the objective function has a negative curvature around each saddle point. This structure allows a number of iterative optimization methods to efficiently find a global minimizer, without special initialization. To corroborate the claim, we describe and analyze a second-order trust-region algorithm.

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。

↑