arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2112.07993math.NAcs.ITcs.NAmath.IT
收藏

相位恢复的全球景观I:扰动振幅模型

The global landscape of phase retrieval I: perturbed amplitude models

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

摘要:

相位恢复中的基本任务是从一组仅幅度测量值$y_i=\abs{\nj{\va_i,\vx}}, \; i=1,\ldots,m$中恢复未知信号$\vx\in \Rn$。在本文中,我们提出了两个新的扰动振幅模型(PAM),具有非凸和二次型损失函数。当测量值$ \va_i \in \Rn$为高斯随机向量且测量值个数为$m\ge Cn$时,我们严格证明了PAM不存在高概率的伪局部极小点,即,目标解$ \vx$是唯一的全局最小值(直到全局阶段),并且损失函数在每个鞍点周围具有负方向曲率。由于良好驯服的良性几何景观,可以采用香草梯度下降法来定位全局极小值$\vx$(直到全局相位),而无需谱初始化。我们进行了大量的数值实验表明,梯度下降算法与随机初始化优于国家的最先进的算法与谱初始化的经验成功率和收敛速度。

英文摘要:

A fundamental task in phase retrieval is to recover an unknown signal $\vx\in \Rn$ from a set of magnitude-only measurements $y_i=\abs{\nj{\va_i,\vx}}, \; i=1,\ldots,m$. In this paper, we propose two novel perturbed amplitude models (PAMs) which have non-convex and quadratic-type loss function. When the measurements $ \va_i \in \Rn$ are Gaussian random vectors and the number of measurements $m\ge Cn$, we rigorously prove that the PAMs admit no spurious local minimizers with high probability, i.e., the target solution $ \vx$ is the unique global minimizer (up to a global phase) and the loss function has a negative directional curvature around each saddle point. Thanks to the well-tamed benign geometric landscape, one can employ the vanilla gradient descent method to locate the global minimizer $\vx$ (up to a global phase) without spectral initialization. We carry out extensive numerical experiments to show that the gradient descent algorithm with random initialization outperforms state-of-the-art algorithms with spectral initialization in empirical success rate and convergence speed.

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。

↑