On the Convergence Rate of Projected Gradient Descent for a Back-Projection Based Objective

DOI10.1137/21M1407902zbMath1474.65183arXiv2005.00959OpenAlexW3207756131MaRDI QIDQ5860373

Tom Tirer, Raja Giryes

Publication date: 19 November 2021

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

Full work available at URL: https://arxiv.org/abs/2005.00959

zbMATH Keywords

inverse problemsimage restorationproximal gradient methodprojected gradient descent

Mathematics Subject Classification ID

Image analysis in multivariate analysis (62H35) Numerical optimization and variational techniques (65K10) Computing methodologies for image processing (68U10) Image processing (compression, reconstruction, etc.) in information and communication theory (94A08)

Uses Software

• Adam
• DnCNN
• ALISTA

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Nonlinear total variation based noise removal algorithms
• A Fast Iterative Shrinkage-Thresholding Algorithm for Linear Inverse Problems
• Estimation of the mean of a multivariate normal distribution
• The convex geometry of linear inverse problems
• \(\ell^1\)-analysis minimization and generalized (co-)sparsity: when does recovery succeed?
• Generalized Alternating Projection for Weighted-$\ell_{2,1}$ Minimization with Applications to Model-Based Compressive Sensing
• Robust 1-bit Compressed Sensing and Sparse Logistic Regression: A Convex Programming Approach
• Generalized SURE for Exponential Families: Applications to Regularization
• First-Order Methods in Optimization
• A Convergent Image Fusion Algorithm Using Scene-Adapted Gaussian-Mixture-Based Denoising
• Image Restoration by Iterative Denoising and Backward Projections
• Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
• An iterative thresholding algorithm for linear inverse problems with a sparsity constraint
• De-noising by soft-thresholding
• Back-Projection Based Fidelity Term for Ill-Posed Linear Inverse Problems
• Living on the edge: phase transitions in convex programs with random data
• Image Super-Resolution Via Sparse Representation
• An Augmented Lagrangian Approach to the Constrained Optimization Formulation of Imaging Inverse Problems
• BM3D Frames and Variational Image Deblurring
• Sharp Time–Data Tradeoffs for Linear Inverse Problems
• Proximité et dualité dans un espace hilbertien
• Compressed sensing

This page was built for publication: On the Convergence Rate of Projected Gradient Descent for a Back-Projection Based Objective