Sparse phase retrieval via ℓp(0<p≤1) minimization.

In this paper, the ℓ 1 -analysis model for the phase retrieval problem of sparse unknown signals in the redundant dictionary is extended to the ℓ p -analysis model, where 0 < p ≤ 1. It's shown that if the measurement matrix A satisfies the strong restricted isometry property adapted to D (S-DRIP) condition, the unknown signal x can be stably recovered by analyzing the ℓ p (0 < p ≤ 1) minimization model. [ABSTRACT FROM AUTHOR]