5 papers
Newton-Direction-Based ReLU-Thresholding Methods for Nonnegative Sparse Signal Recovery
Ning Bian, Zhong-Feng Sun, Yun-Bin Zhao +2
Nonnegative sparse signal recovery has been extensively studied due to its broad applications. Recent work has integrated rectified linear unit (ReLU) techniques to enhance existin…
Optimality Conditions for Sparse Bilinear Least Squares Problems
Zixin Deng, Zheng-Hai Huang, Yun-Bin Zhao
The first-order optimality conditions of sparse bilinear least squares problems are studied. The so-called T-type and N-type stationary points for this problem are characterized in…
Compressed Newton-direction-based Thresholding Methods for Sparse Optimization Problems
Nan Meng, Yun-Bin Zhao
Thresholding algorithms for sparse optimization problems involve two key components: search directions and thresholding strategies. In this paper, we use the compressed Newton dire…
Reinforcement-learning-based Algorithms for Optimization Problems and Applications to Inverse Problems
Chen Xu, Yun-Bin Zhao, Zhipeng Lu +1
We design a new iterative algorithm, called REINFORCE-OPT, for solving a general type of optimization problems. This algorithm parameterizes the solution search rule and iterativel…
On NP-Hardness of Minimization and Bound Theory of Nonzero Entries in Solutions
Min Tao, Xiao-Ping Zhang, Yun-Bin Zhao
The \(L_1/L_2\) norm ratio has gained significant attention as a measure of sparsity due to three merits: sharper approximation to the \(L_0\) norm compared to the \(L_1\) norm, be…