Phase Retrieval via Randomized Kaczmarz: Theoretical Guarantees. Tan, YS; Vershynin, R

We consider the problem of phase retrieval, i.e. that of solving systems of quadratic equations. A simple variant of randomized Kaczmarz method was recently proposed for phase retrieval, and it was shown numerically to have a computational edge over state-of-the-art Wirtinger flow methods. In this paper, we provide the first theoretical guarantee for the convergence of the randomized Kacmarz method for phase retrieval. We show that it is sufficient to have as many gaussian measurements as the dimension, up to a constant factor. Along the way, we introduce a sufficient condition on measurement sets for which the randomized Kaczmarz method is guaranteed to work. We show that gaussian measurements satisfy this property with high probability; this is proved using a chaining argument coupled with bounds on VC dimension and metric entropy.

from # & - All via ola Kala on Inoreader http://ift.tt/2eLjAku