标题： 多阶段凸松弛用于特征选择 显示英文标题

标题： Multi-stage Convex Relaxation for Feature Selection

摘要： 许多近期的工作研究了使用 Lasso 进行特征选择的有效性。已知在受限等距性质（RIP）下，由于凸松弛的松散性，Lasso 通常不能实现非零系数集合的精确恢复。本文考虑了非凸正则化的特征选择特性，其中解由多阶段凸松弛方案给出。在适当的条件下，我们证明了该过程得到的局部解能够无偏地恢复非零系数集合，这补充了该过程的参数估计结果。 显示英文摘要

摘要： 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. Under appropriate conditions, we show that 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.