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,...
Auteurs principaux: | Wu, F, Rebeschini, P |
---|---|
Format: | Conference item |
Langue: | English |
Publié: |
Journal of Machine Learning Research
2021
|
Documents similaires
-
A continuous-time mirror descent approach to sparse phase retrieval
par: Wu, F, et autres
Publié: (2020) -
Pixel Super-Resolution Phase Retrieval for Lensless On-Chip Microscopy via Accelerated Wirtinger Flow
par: Yunhui Gao, et autres
Publié: (2022-06-01) -
Nearly minimax-optimal rates for noisy sparse phase retrieval via early-stopped mirror descent
par: Wu, F, et autres
Publié: (2022) -
Research of Phase Compensation Methods Based on the Median Reweighted Wirtinger Flow Algorithm
par: Yang Cao, et autres
Publié: (2022-08-01) -
Wirtinger-Beesack integral inequalities
par: Gulomjon M. Muminov
Publié: (2005-09-01)