期刊
BERNOULLI
卷 19, 期 5B, 页码 2277-2293出版社
INT STATISTICAL INST
DOI: 10.3150/12-BEJ452
关键词
multi-stage convex relaxation; non-convex penalty; variable selection
资金
- NSF [DMS-10-07527, IIS-1016061]
- [AFOSR-10097389]
- [NSA-AMS 081024]
- Direct For Computer & Info Scie & Enginr
- Div Of Information & Intelligent Systems [1016061] Funding Source: National Science Foundation
A number of recent work studied the effectiveness of feature selection using Lasso. It is known that under the restricted isometry properties (RIP), Lasso does not generally lead to the exact recovery of the set of nonzero coefficients, due to the looseness of convex relaxation. This paper considers the feature selection property of nonconvex regularization, where the solution is given by a multi-stage convex relaxation scheme. The nonconvex regularizer requires two tuning parameters (compared to one tuning parameter for Lasso). Although the method is more complex than Lasso, we show that under appropriate conditions including the dependence of a tuning parameter on the support set size, the local solution obtained by this procedure recovers the set of nonzero coefficients without suffering from the bias of Lasso relaxation, which complements parameter estimation results of this procedure in (J. Mach. Learn. Res. 11 (2011) 1087-1107).
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据