arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2002.10913math.OC
收藏

稀疏恢复的临界点理论

Critical point theory for sparse recovery

Sebastian Lämmel, Vladimir Shikhman

摘要:

我们研究了压缩感知背景下的稀疏恢复问题。这是为了通过具有至多$s$非零条目的稀疏向量来最小化线性测量的感测误差。我们开发了所谓的临界点理论稀疏恢复。这是通过引入非退化M-平稳点,充分描述了这个非凸最优化问题的全局结构。我们证明了所有M-驻点都是一般非退化的。特别是,稀疏约束是积极的,在所有的局部极小的一个通用的稀疏恢复问题。此外,还证明了M-平稳点的强稳定性与非退化性的等价性.我们声称,鞍点的出现-这些都是M-平稳点,正好$s-1$非零条目-不能忽略。为此,我们推导出一个所谓的莫尔斯关系,它给出了一个下界的鞍点的数量方面的局部极小。鞍点的相对复杂的结构可以被看作是解决稀疏恢复到全局最优的问题的一个众所周知的困难的来源。

英文摘要:

We study the problem of sparse recovery in the context of compressed sensing. This is to minimize the sensing error of linear measurements by sparse vectors with at most $s$ non-zero entries. We develop the so-called critical point theory for sparse recovery. This is done by introducing nondegenerate M-stationary points which adequately describe the global structure of this nonconvex optimization problem. We show that all M-stationary points are generically nondegenerate. In particular, the sparsity constraint is active at all local minimizers of a generic sparse recovery problem. Additionally, the equivalence of strong stability and nondegeneracy for M-stationary points is shown. We claim that the appearance of saddle points - these are M-stationary points with exactly $s-1$ non-zero entries - cannot be neglected. For this purpose we derive a so-called Morse relation, which gives a lower bound on the number of saddle points in terms of the number of local minimizers. The relatively involved structure of saddle points can be seen as a source of well-known difficulty by solving the problem of sparse recovery to global optimality.

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。

↑