.png){kind=icon}
返回
A Simple Neural Network for Sparse Optimization With l1 Regularization
.png){kind=icon}
PRE
AI
DOI：10.1109/TNSE.2021.3114426.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
This paper considers a class of sparse optimization problems with l(1)-norm regularization and general convex constraints, in which the individual functions involved are differential except l(1) regularization term. Firstly, a sufficient and necessary condition for the subgradients of l(1)-norm is discussed. Subsequently, a sufficient and necessary optimality condition for the considered problem is obtained. According to this condition, a simple neural network with differential equation structure is proposed. Secondly, positive invariance and exponential convergence of state trajectory to the set of equality constraints are studied. In addition, the intermediate state variable is always non-negative when its initial value is so. Moreover, boundedness, global existence and stability in the sense of Lyapunov of state solution to the proposed neural network are guaranteed. Thirdly, the proposed network is globally convergent to an optimal solution of the considered problem from any initial point. At last, sufficient experiments including two numerical experiments, signal recovery, data classification and image restoration problems with real data sets are provided to show the efficiency of this approach.
Keyword:
l(1)-norm
Sparse optimization
Neurodynamic approach
General convex constraints
Projection operator
期刊
I
IF:
7.9
论文数:
2.5K
被引数:
10.0K
机构
引用论文
Integrated Optimization Design of Combined Cooling, Heating, and Power System Coupled with Solar and Biomass Energy.png)
Energies
OAAI
EnergiesIF0
OAAI分享收藏A Discrete-Time Projection Neural Network for Sparse Signal Reconstruction With Application to Face Recognition稀疏信号重构的离散时间投影神经网络及其在人脸识别中的应用
PREAI
分享收藏分享收藏
查看更多内容