Exact Recovery of Multichannel Sparse Blind Deconvolution via Gradient Descent

DOI10.1137/19M1291327zbMath1456.65043OpenAlexW3087723003MaRDI QIDQ5143310

Zhihui Zhu, Xiao Li, Qing Qu

Publication date: 11 January 2021

Published in: SIAM Journal on Imaging Sciences (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1137/19m1291327

zbMATH Keywords

inverse problemRiemannian manifoldnonconvex optimizationnonlinear approximationblind deconvolutionsparse recoverynonconvex geometry

Mathematics Subject Classification ID

Numerical mathematical programming methods (65K05) Nonconvex programming, global optimization (90C26) Computing methodologies for image processing (68U10) Numerical aspects of computer graphics, image analysis, and computational geometry (65D18) Signal theory (characterization, reconstruction, filtering, etc.) (94A12) Complexity and performance of numerical algorithms (65Y20)

Uses Software

• CVX

Cites Work

• Unnamed Item
• Unnamed Item
• Subgradient methods for sharp weakly convex functions
• Implicit regularization in nonconvex statistical estimation: gradient descent converges linearly for phase retrieval, matrix completion, and blind deconvolution
• Rapid, robust, and reliable blind deconvolution via nonconvex optimization
• Gradient descent with random initialization: fast global convergence for nonconvex phase retrieval
• Tail bounds via generic chaining
• Identifiability in Blind Deconvolution With Subspace or Sparsity Constraints
• Phase Retrieval via Wirtinger Flow: Theory and Algorithms
• Blind Deconvolution Using Convex Programming
• Identifiability in Bilinear Inverse Problems With Applications to Subspace or Sparsity-Constrained Blind Gain and Phase Calibration
• Complete Dictionary Recovery Over the Sphere I: Overview and the Geometric Picture
• Complete Dictionary Recovery Over the Sphere II: Recovery by Riemannian Trust-Region Method
• Weak Sharp Minima in Mathematical Programming
• Self-calibration and biconvex compressive sensing
• The Null Space Problem I. Complexity
• On convergence rates of subgradient optimization methods
• Recovery of Sparse Translation-Invariant Signals With Continuous Basis Pursuit
• Convolutional Dictionary Learning: Acceleration and Convergence
• Non-convex Optimization for Machine Learning
• Fast and Guaranteed Blind Multichannel Deconvolution Under a Bilinear System Model
• Self-Calibration and Bilinear Inverse Problems via Linear Least Squares
• Sparse Approximate Solutions to Linear Systems
• Geometry and Symmetry in Short-and-Sparse Deconvolution
• Convolutional Phase Retrieval via Gradient Descent
• Multichannel Sparse Blind Deconvolution on the Sphere
• Nonconvex Robust Low-Rank Matrix Recovery
• Blind Gain and Phase Calibration via Sparse Spectral Methods
• Spectral Methods for Passive Imaging: Nonasymptotic Performance and Robustness
• Nonconvex Optimization Meets Low-Rank Matrix Factorization: An Overview
• Fast, robust and non-convex subspace recovery
• Optimal Injectivity Conditions for Bilinear Inverse Problems with Applications to Identifiability of Deconvolution Problems
• Robust Multichannel Blind Deconvolution via Fast Alternating Minimization
• Leveraging Diversity and Sparsity in Blind Deconvolution
• Upper and Lower Bounds for Stochastic Processes

This page was built for publication: Exact Recovery of Multichannel Sparse Blind Deconvolution via Gradient Descent