Smoothing inertial projection neural network for minimization \(L_{p-q}\) in sparse signal reconstruction

DOI10.1016/j.neunet.2017.12.008zbMath1456.94024OpenAlexW2777821919WikidataQ47196351 ScholiaQ47196351MaRDI QIDQ2179318

Junjian Huang, You Zhao, Xing He, Tingwen Huang

Publication date: 12 May 2020

Published in: Neural Networks (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.neunet.2017.12.008

zbMATH Keywords

sparse signal recovery\(L_{p-q}\) minimizationrestricted isometry property (RIP) conditionsmoothing inertial projection neural network (SIPNN)

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Nonconvex programming, global optimization (90C26) Signal theory (characterization, reconstruction, filtering, etc.) (94A12)

Related Items (6)

A smoothing inertial neural network for sparse signal reconstruction with noise measurements via \(L_p-L_1\) minimization ⋮ Cardinality-constrained portfolio selection based on collaborative neurodynamic optimization ⋮ Block-sparse recovery and rank minimization using a weighted \(l_p-l_q\) model ⋮ Sparse signal reconstruction via collaborative neurodynamic optimization ⋮ Neurodynamic approaches for sparse recovery problem with linear inequality constraints ⋮ Smoothing inertial neurodynamic approach for sparse signal reconstruction via \(L_p\)-norm minimization

Cites Work

• Unnamed Item
• Distributed Optimization and Statistical Learning via the Alternating Direction Method of Multipliers
• Neural network for solving Nash equilibrium problem in application of multiuser power control
• Thresholding-based iterative selection procedures for model selection and shrinkage
• Collective neurodynamic optimization for economic emission dispatch problem considering valve point effect in microgrid
• Generalized sparse recovery model and its neural dynamical optimization method for compressed sensing
• Complexity of unconstrained \(L_2 - L_p\) minimization
• A Method for Finding Structured Sparse Solutions to Nonnegative Least Squares Problems with Applications
• Alternating Direction Algorithms for $\ell_1$-Problems in Compressive Sensing
• Robust uncertainty principles: exact signal reconstruction from highly incomplete frequency information
• Decoding by Linear Programming
• Signal Recovery From Random Measurements Via Orthogonal Matching Pursuit
• An Introduction to Variational Inequalities and Their Applications
• <formula formulatype="inline"><tex Notation="TeX">$L_{1/2}$</tex> </formula> Regularization: Convergence of Iterative Half Thresholding Algorithm
• Sparse Approximate Solutions to Linear Systems
• L 1/2 regularization
• Minimization of $\ell_{1-2}$ for Compressed Sensing
• Compressed sensing

This page was built for publication: Smoothing inertial projection neural network for minimization \(L_{p-q}\) in sparse signal reconstruction