相位恢复II的全球景观:商强度模型
The global landscape of phase retrieval II: quotient intensity models
摘要:
相位恢复中的一个基本问题是从一组仅测量幅度的测量值中重建未知信号。在这项工作中,我们介绍了三个新的商强度为基础的模型(QIMs)的基础上深入修改传统的强度为基础的模型。新的损失函数的一个显著特点是在最优采样复杂度下对应的几何景观是良性的。当测量值$ a_i\in \Rn$是高斯随机向量并且测量值的数目为$m\ge Cn$时,QIM不允许具有高概率的伪局部最小值,即,目标解$ x$是唯一的全局最小值(直到全局相位),并且损失函数具有围绕每个鞍点的负方向曲率。这种良性的几何景观允许梯度下降法找到全局解$x$(直到全局相位),而无需谱初始化。
英文摘要:
A fundamental problem in phase retrieval is to reconstruct an unknown signal from a set of magnitude-only measurements. In this work we introduce three novel quotient intensity-based models (QIMs) based a deep modification of the traditional intensity-based models. A remarkable feature of the new loss functions is that the corresponding geometric landscape is benign under the optimal sampling complexity. When the measurements $ a_i\in \Rn$ are Gaussian random vectors and the number of measurements $m\ge Cn$, the QIMs admit no spurious local minimizers with high probability, i.e., the target solution $ x$ is the unique global minimizer (up to a global phase) and the loss function has a negative directional curvature around each saddle point. Such benign geometric landscape allows the gradient descent methods to find the global solution $x$ (up to a global phase) without spectral initialization.
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。