| 摘要: |
| 本文研究了一类稀疏正则化的非凸优化问题.利用近端梯度法，获得了其全局收敛的结果，推广了算法模型在神经网络训练中的应用. |
| 关键词: 非凸组合优化 稀疏正则化 近端梯度 |
| DOI： |
| 分类号:O224 |
| 基金项目:国家自然科学基金委员会 (61179039); 国家重点基础研究发展规划项目 (973 计划项目)(2011CB707100). |
|
| GLOBAL CONVERGENCE ANALYSIS OF SPARSE REGULAR NONCONVEX OPTIMIZATION PROBLEMS |
|
CHU Min
|
|
School of Mathematics and Statistics, Wuhan University, Wuhan 430072, China
|
| Abstract: |
| In this paper, we consider a class of sparse regularization nonconvex optimization problems. By using the proximal gradient method, we obtain the global convergence results, which generalize application of algorithm models in neural network training. |
| Key words: nonconvex composite optimization sparse regularization proximal gradient |
