Hadamard Wirtinger Flow for Sparse Phase Retrieval
This work addresses sparse phase retrieval, a problem in signal processing and imaging, by offering an incremental improvement in sample complexity and runtime for reconstruction algorithms.
The paper tackles the problem of reconstructing sparse signals from magnitude-only measurements by proposing Hadamard Wirtinger Flow (HWF), a gradient descent method with Hadamard parametrization, which achieves support recovery with sample complexity linear in sparsity k when the signal has a large component and reduces measurements compared to existing gradient-based methods.
We consider the problem of reconstructing an $n$-dimensional $k$-sparse signal from a set of noiseless magnitude-only measurements. Formulating the problem as an unregularized empirical risk minimization task, we study the sample complexity performance of gradient descent with Hadamard parametrization, which we call Hadamard Wirtinger flow (HWF). Provided knowledge of the signal sparsity $k$, we prove that a single step of HWF is able to recover the support from $k(x^*_{max})^{-2}$ (modulo logarithmic term) samples, where $x^*_{max}$ is the largest component of the signal in magnitude. This support recovery procedure can be used to initialize existing reconstruction methods and yields algorithms with total runtime proportional to the cost of reading the data and improved sample complexity, which is linear in $k$ when the signal contains at least one large component. We numerically investigate the performance of HWF at convergence and show that, while not requiring any explicit form of regularization nor knowledge of $k$, HWF adapts to the signal sparsity and reconstructs sparse signals with fewer measurements than existing gradient based methods.