arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1106.4355stat.MLcs.LG
收藏

结构稀疏信号精确恢复的紧测量界

Tight Measurement Bounds for Exact Recovery of Structured Sparse Signals

University of Wisconsin-Madison(威斯康星大学麦迪逊分校)

Nikhil Rao, Benjamin Recht, Robert Nowak

摘要:

标准压缩感测结果表明,为了精确地恢复R ^p中的s稀疏信号,需要O(s)。log(p))测量。虽然这个界限在实践中非常有用,但现实世界的信号往往不仅稀疏,而且还表现出稀疏模式的结构。本文主要研究群体结构模式。在该模型下,信号系数组一起是活动的(或非活动的)。组是预定义的,但是活动的组的特定集合(即,在信号支持中)必须从测量中学习。我们表明,利用知识的群体,可以进一步减少所需的精确信号恢复测量的数量,并推导出所需的测量数量的普遍界限。这个界限是普遍的,因为它只取决于所考虑的群体的数量,而不取决于群体的具体情况(例如,组成、大小、范围、重叠等)。实验表明,我们的结果适用于各种重叠群配置。

英文摘要:

Standard compressive sensing results state that to exactly recover an s sparse signal in R^p, one requires O(s. log(p)) measurements. While this bound is extremely useful in practice, often real world signals are not only sparse, but also exhibit structure in the sparsity pattern. We focus on group-structured patterns in this paper. Under this model, groups of signal coefficients are active (or inactive) together. The groups are predefined, but the particular set of groups that are active (i.e., in the signal support) must be learned from measurements. We show that exploiting knowledge of groups can further reduce the number of measurements required for exact signal recovery, and derive universal bounds for the number of measurements needed. The bound is universal in the sense that it only depends on the number of groups under consideration, and not the particulars of the groups (e.g., compositions, sizes, extents, overlaps, etc.). Experiments show that our result holds for a variety of overlapping group configurations.

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。

↑