一类零模正则复合优化问题的多阶段凸松弛法

GEP-MSCRA for a Kind of Zero-Norm Regularized Composite Optimization Problem

本文从零模函数的变分刻画入手,将这类带有组合性质的优化问题等价转化为具有拟双线性结构且全局Lipshitz连续的优化模型,以此设计了求解零模正则化复合优化问题的多阶段凸松弛方法,并对该方法进行了收敛性分析。

This article starts from the variational characterization of zero-norm, then changes such a combi-nation optimization problem to an equivalent model which has bi-linear structure and global Lip-schitz continuous. This article also designed multi-stage convex relaxation methods to solve the zero-norm regularized composite optimization problem, and analyzed the convergence for it.