|
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
|
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 |