Regularized gradient descent: a non-convex recipe for fast joint blind deconvolution and demixing

DOI10.1093/imaiai/iax022zbMath1470.94047arXiv1703.08642OpenAlexW2963430899MaRDI QIDQ5242863

Shuyang Ling, Thomas Strohmer

Publication date: 7 November 2019

Published in: Information and Inference: A Journal of the IMA (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1703.08642

zbMATH Keywords

random matrixsignal processingnon-convex optimizationwireless communicationblind deconvolutionexact recoveryblind demixingnon-convex algorithm

Mathematics Subject Classification ID

Random matrices (probabilistic aspects) (60B20) Nonconvex programming, global optimization (90C26) Signal theory (characterization, reconstruction, filtering, etc.) (94A12)

Related Items (11)

The numerics of phase retrieval ⋮ Robust recovery of low-rank matrices with non-orthogonal sparse decomposition from incomplete measurements ⋮ Implicit regularization in nonconvex statistical estimation: gradient descent converges linearly for phase retrieval, matrix completion, and blind deconvolution ⋮ Convex and Nonconvex Optimization Are Both Minimax-Optimal for Noisy Blind Deconvolution Under Random Designs ⋮ Riemannian thresholding methods for row-sparse and low-rank matrix recovery ⋮ Performance bounds of the intensity-based estimators for noisy phase retrieval ⋮ Painless breakups -- efficient demixing of low rank matrices ⋮ A convex variational model for learning convolutional image atoms from incomplete data ⋮ Sparse power factorization: balancing peakiness and sample complexity ⋮ Estimation from nonlinear observations via convex programming with application to bilinear regression ⋮ The basins of attraction of the global minimizers of the non-convex sparse spike estimation problem

This page was built for publication: Regularized gradient descent: a non-convex recipe for fast joint blind deconvolution and demixing