Hadamard wirtinger flow for sparse phase retrieval

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,...

Полное описание

Библиографические подробности
Главные авторы: Wu, F, Rebeschini, P
Формат: Conference item
Язык:English
Опубликовано: Journal of Machine Learning Research 2021

Схожие документы