arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1902.04731math.NAcs.NA
收藏

联合低秩和二分恢复:问题和部分答案

Jointly Low-Rank and Bisparse Recovery: Questions and Partial Answers

Simon Foucart, Rémi Gribonval, Laurent Jacques, Holger Rauhut

摘要:

我们调查的问题,恢复联合$r$秩和$s$双解析矩阵从尽可能少的线性测量,考虑任意测量以及秩一测量。在这两种情况下,我们表明,$m \asymp r s \ln(en/s)$测量使恢复在理论上是可能的,这意味着通过一个不切实际的算法。在任意测量的情况下,我们研究了当$m \asymp r s^γ\ln(en/s)$为某个指数$γ> 0$时,通过迭代硬阈值算法实现实际恢复的可能性。我们表明,这是可行的$γ= 2$,提出的分析不能涵盖的情况下$γ\leq 1$。最优指数$γ\in [1,2]$的精确值是本文提出但未解决的关于联合低秩双解析结构的头部投影的问题的目标。一些相关的问题在这里得到了部分的回答。对于秩一测量,我们建议在《双城之战》神秘的理由迭代硬阈值算法修改,以利用非标准的限制等距属性服从这类测量。

英文摘要:

We investigate the problem of recovering jointly $r$-rank and $s$-bisparse matrices from as few linear measurements as possible, considering arbitrary measurements as well as rank-one measurements. In both cases, we show that $m \asymp r s \ln(en/s)$ measurements make the recovery possible in theory, meaning via a nonpractical algorithm. In case of arbitrary measurements, we investigate the possibility of achieving practical recovery via an iterative-hard-thresholding algorithm when $m \asymp r s^γ\ln(en/s)$ for some exponent $γ> 0$. We show that this is feasible for $γ= 2$, and that the proposed analysis cannot cover the case $γ\leq 1$. The precise value of the optimal exponent $γ\in [1,2]$ is the object of a question, raised but unresolved in this paper, about head projections for the jointly low-rank and bisparse structure. Some related questions are partially answered in passing. For rank-one measurements, we suggest on arcane grounds an iterative-hard-thresholding algorithm modified to exploit the nonstandard restricted isometry property obeyed by this type of measurements.

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。

↑