Relaxed sparse eigenvalue conditions for sparse estimation via non-convex regularized regression
作者：
Highlights：
• We give new weaker conditions for sparse estimation with non-convex regularizers.
• Our regularizers are general, including many existing non-convex regularizers.
• Our estimation conditions are applicable even when the solutions is suboptimal.
• The desired suboptimal solutions can be obtained by coordinate descent.
摘要
Highlights•We give new weaker conditions for sparse estimation with non-convex regularizers.•Our regularizers are general, including many existing non-convex regularizers.•Our estimation conditions are applicable even when the solutions is suboptimal.•The desired suboptimal solutions can be obtained by coordinate descent.
论文关键词：Sparse estimation,Non-convex regularization,Sparse eigenvalue,Coordinate descent
论文评审过程：Received 30 June 2013, Revised 23 January 2014, Accepted 19 June 2014, Available online 30 June 2014.
论文官网地址：https://doi.org/10.1016/j.patcog.2014.06.018
