arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2311.08833eess.SPcs.ITmath.IT
收藏

基于半代数与 ReLU 神经网络先验的相位恢复

Phase retrieval with semi-algebraic and ReLU neural network priors

Tamir Bendory, Nadav Dym, Dan Edidin, Arun Suresh

AI总结:

本文研究信号位于半代数集合先验下的相位恢复问题,证明维数为N/2或N/4的半代数集合中的信号可由傅里叶幅值确定,并将结果推广至多参考对齐及球面带限函数恢复,给出了改进的样本复杂度界限。

摘要:

从傅里叶幅值中恢复信号(即解决相位恢复问题)的关键要素是对目标信号施加有效的先验。本文在信号位于半代数集合中的先验条件下研究相位恢复问题。这是一个非常通用的先验,因为半代数集合包含线性模型、稀疏模型和 ReLU 神经网络生成模型。由于深度生成模型在包括相位恢复在内的各种成像任务中取得了显著成功,后者是本文的主要动机。我们证明,如果 R^N 中的信号位于维数为 N/2 的(通用)半代数集合中,则几乎所有信号都可以从其傅里叶幅值中确定(仅差一个符号)。如果半代数集合的维数为 N/4,则对于所有信号同样成立。我们还将这些结果推广到多参考对齐模型中基于二阶矩的信号恢复问题,该模型具有紧群的无关重数的表示。随后,利用这一通用结果推导出了改进的样本复杂度界限,用于从球面上的带限函数的带噪副本中恢复该函数,其中每个副本均受到 SO(3) 随机元素的作用。

英文摘要:

The key ingredient to retrieving a signal from its Fourier magnitudes, namely, to solve the phase retrieval problem, is an effective prior on the sought signal. In this paper, we study the phase retrieval problem under the prior that the signal lies in a semi-algebraic set. This is a very general prior as semi-algebraic sets include linear models, sparse models, and ReLU neural network generative models. The latter is the main motivation of this paper, due to the remarkable success of deep generative models in a variety of imaging tasks, including phase retrieval. We prove that almost all signals in R^N can be determined from their Fourier magnitudes, up to a sign, if they lie in a (generic) semi-algebraic set of dimension N/2. The same is true for all signals if the semi-algebraic set is of dimension N/4. We also generalize these results to the problem of signal recovery from the second moment in multi-reference alignment models with multiplicity free representations of compact groups. This general result is then used to derive improved sample complexity bounds for recovering band-limited functions on the sphere from their noisy copies, each acted upon by a random element of SO(3).

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。

↑