Convergence of the randomized Kaczmarz method for phase retrieval
This establishes theoretical convergence for a simple iterative method in phase retrieval, a problem where such guarantees were previously lacking.
The paper provides the first rigorous convergence guarantee for the randomized Kaczmarz method applied to phase retrieval, showing that with high probability, a random measurement system of size m ≈ d ensures exponential convergence in the mean square sense, comparable to the linear setting.
The classical Kaczmarz iteration and its randomized variants are popular tools for fast inversion of linear overdetermined systems. This method extends naturally to the setting of the phase retrieval problem via substituting at each iteration the phase of any measurement of the available approximate solution for the unknown phase of the measurement of the true solution. Despite the simplicity of the method, rigorous convergence guarantees that are available for the classical linear setting have not been established so far for the phase retrieval setting. In this short note, we provide a convergence result for the randomized Kaczmarz method for phase retrieval in $\mathbb{R}^d$. We show that with high probability a random measurement system of size $m \asymp d$ will be admissible for this method in the sense that convergence in the mean square sense is guaranteed with any prescribed probability. The convergence is exponential and comparable to the linear setting.