A Semismooth Newton Algorithm for High-Dimensional Nonconvex Sparse Learning
A Semismooth Newton Algorithm for High-Dimensional Nonconvex Sparse Learning
复制标题
高维非凸稀疏学习的半光滑牛顿算法
DOI:
10.1109/tnnls.2019.2935001
复制
发表时间:
2018-02
影响因子:
10.4
通讯作者:
Yang Qinglong
中科院分区:
文献类型:
--
作者:
Shi Yueyong;Huang Jian;Jiao Yuling;Yang Qinglong
The smoothly clipped absolute deviation (SCAD) and the minimax concave penalty (MCP)-penalized regression models are two important and widely used nonconvex sparse learning tools that can handle variable selection and parameter estimation simultaneously and thus have potential applications in various fields, such as mining biological data in high-throughput biomedical studies. Theoretically, these two models enjoy the oracle property even in the high-dimensional settings, where the number of predictors <inline-formula> <tex-math notation="LaTeX">$p$ </tex-math></inline-formula> may be much larger than the number of observations <inline-formula> <tex-math notation="LaTeX">$n$ </tex-math></inline-formula>. However, numerically, it is quite challenging to develop fast and stable algorithms due to their nonconvexity and nonsmoothness. In this article, we develop a fast algorithm for SCAD- and MCP-penalized learning problems. First, we show that the global minimizers of both models are roots of the nonsmooth equations. Then, a semismooth Newton (SSN) algorithm is employed to solve the equations. We prove that the SSN algorithm converges locally and superlinearly to the Karush–Kuhn–Tucker (KKT) points. The computational complexity analysis shows that the cost of the SSN algorithm per iteration is <inline-formula> <tex-math notation="LaTeX">$O(np)$ </tex-math></inline-formula>. Combined with the warm-start technique, the SSN algorithm can be very efficient and accurate. Simulation studies and a real data example suggest that our SSN algorithm, with comparable solution accuracy with the coordinate descent (CD) and the difference of convex (DC) proximal Newton algorithms, is more computationally efficient.
登录
查看更多内容
DOI:
--
发表时间:
2014-03
期刊:
ArXiv
影响因子:
--
作者:
Yuling Jiao;Bangti Jin;Xiliang Lu
通讯作者:
Yuling Jiao;Bangti Jin;Xiliang Lu
DOI:
--
发表时间:
2019-01
期刊:
arXiv: Computer Vision and Pattern Recognition
影响因子:
--
作者:
Rongrong Ma;Jianyu Miao;Lingfeng Niu;Peng Zhang
通讯作者:
Rongrong Ma;Jianyu Miao;Lingfeng Niu;Peng Zhang
DOI:
--
发表时间:
2017-06
期刊:
ArXiv
影响因子:
--
作者:
Xingguo Li;Lin F. Yang;J. Ge;Jarvis D. Haupt;T. Zhang;T. Zhao
通讯作者:
Xingguo Li;Lin F. Yang;J. Ge;Jarvis D. Haupt;T. Zhang;T. Zhao
影响因子:
2.1
作者:
Becker, Stephen;Bobin, Jerome;Candes, Emmanuel J.
通讯作者:
Candes, Emmanuel J.
影响因子:
4.5
作者:
Zhang, Cun-Hui
通讯作者:
Zhang, Cun-Hui