Sample-Efficient Sparse Phase Retrieval via Stochastic Alternating Minimization
Abstract
In this work we propose a nonconvex two-stage \underline{s}tochastic \underline{a}lternating \underline{m}inimizing (SAM) method for sparse phase retrieval. The proposed algorithm is guaranteed to have an exact recovery from samples if provided the initial guess is in a local neighbour of the ground truth. Thus, the proposed algorithm is two-stage, first we estimate a desired initial guess (e.g. via a spectral method), and then we introduce a randomized alternating minimization strategy for local refinement. Also, the hard-thresholding pursuit algorithm is employed to solve the sparse constraint least square subproblems. We give the theoretical justifications that SAM find the underlying signal exactly in a finite number of iterations (no more than steps) with high probability. Further, numerical experiments illustrates that SAM requires less measurements than state-of-the-art algorithms for sparse phase retrieval problem.
Cite
@article{arxiv.2112.07919,
title = {Sample-Efficient Sparse Phase Retrieval via Stochastic Alternating Minimization},
author = {Jian-Feng Cai and Yuling Jiao and Xiliang Lu and Juntao You},
journal= {arXiv preprint arXiv:2112.07919},
year = {2022}
}