Learnable Descent Algorithm for Nonsmooth Nonconvex Image Reconstruction
From MaRDI portal
Publication:5860374
DOI10.1137/20M1353368zbMath1474.90353arXiv2007.11245OpenAlexW3206437644MaRDI QIDQ5860374
Hongcheng Liu, Yunmei Chen, Qingchao Zhang, Xiaojing Ye
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/2007.11245
Numerical mathematical programming methods (65K05) Nonconvex programming, global optimization (90C26) Numerical optimization and variational techniques (65K10) Computing methodologies for image processing (68U10)
Related Items
An Unrolled Implicit Regularization Network for Joint Image and Sensitivity Estimation in Parallel MR Imaging with Convergence Guarantee, Extrapolated smoothing descent algorithm for constrained nonconvex and nonsmooth composite problems, Bilevel Methods for Image Reconstruction
Uses Software
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Nonlinear total variation based noise removal algorithms
- Smooth minimization of non-smooth functions
- An inertial forward-backward algorithm for the minimization of the sum of two nonconvex functions
- A proximal method for composite minimization
- Global convergence of a proximal linearized algorithm for difference of convex functions
- Gradient methods for minimizing composite functions
- Smoothing methods for nonsmooth, nonconvex minimization
- Properties of the Moreau-Yosida regularization of a piecewise \(C^2\) convex function
- Multilayer feedforward networks are universal approximators
- A proximal difference-of-convex algorithm with extrapolation
- The DC (Difference of convex functions) programming and DCA revisited with DC models of real world nonconvex optimization problems
- Convergence of descent methods for semi-algebraic and tame problems: proximal algorithms, forward-backward splitting, and regularized Gauss-Seidel methods
- Variational networks: an optimal control approach to early stopping variational methods for image restoration
- An algorithm for the minimization of nonsmooth nonconvex functions using inexact evaluations and its worst-case complexity
- A generalized proximal linearized algorithm for DC functions with application to the optimal size of the firm problem
- Error bounds for approximations with deep ReLU networks
- A proximal point method for difference of convex functions in multi-objective optimization with application to group dynamic problems
- Splitting methods with variable metric for Kurdyka-Łojasiewicz functions and general convergence rates
- Non-smooth non-convex Bregman minimization: unification and new algorithms
- An efficient augmented Lagrangian method with applications to total variation minimization
- iPiano: Inertial Proximal Algorithm for Nonconvex Optimization
- Block-Based Compressed Sensing of Images and Video
- From Denoising to Compressed Sensing
- Proximal Alternating Minimization and Projection Methods for Nonconvex Problems: An Approach Based on the Kurdyka-Łojasiewicz Inequality
- Smoothing Projected Gradient Method and Its Application to Stochastic Linear Complementarity Problems
- A generalized proximal point algorithm for certain non-convex minimization problems
- Practical Aspects of the Moreau--Yosida Regularization: Theoretical Preliminaries
- Variational Analysis
- Optimality and Complexity for Constrained Optimization Problems with Nonconvex Regularization
- Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
- AMP-Inspired Deep Networks for Sparse Linear Inverse Problems
- Dual-Path Attention Network for Compressed Sensing Image Reconstruction
- NETT: solving inverse problems with deep neural networks
- Image Denoising Methods. A New Nonlocal Principle
- Error Bounds, Quadratic Growth, and Linear Convergence of Proximal Methods
- On Iteratively Reweighted Algorithms for Nonsmooth Nonconvex Optimization in Computer Vision
- Proximité et dualité dans un espace hilbertien
- A Review of Image Denoising Algorithms, with a New One
- Total Generalized Variation
