arXivDaily arXiv每日学术速递 周一至周五更新
看起来今天可以划水了
arXiv 1912.04498math.OC
收藏

L0复合极小化问题的每个临界点都是局部极小点

Every critical point of an L0 composite minimization problem is a local minimizer

Xue Feng, Chunlin Wu

摘要:

目前,L0最优化模型在许多领域追求稀疏性时显示出了其优越性。对于这类非凸问题,大多数算法只能收敛到其中一个临界点。本文考虑了一般的L0正则极小化问题,其中L0“范数”与一个连续映射合成。在一些温和的假设下,我们证明了这个问题的每个临界点都是局部极小点,从而改进了现有算法的收敛结果。令人惊讶的是,这个结论并不适用于低秩最小化,一个自然的矩阵扩展的L0“范数”的一个向量。

英文摘要:

Nowadays, L0 optimization model has shown its superiority when pursuing sparsity in many areas. For this nonconvex problem, most of the algorithms can only converge to one of its critical points. In this paper, we consider a general L0 regularized minimization problem, where the L0 ''norm'' is composited with a continuous map. Under some mild assumptions, we show that every critical point of this problem is a local minimizer, which improves the convergence results of existing algorithms. Surprisingly, this conclusion does not hold for low rank minimization, a natural matrix extension of L0 ''norm'' of a vector.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑