arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1503.07027cs.LGcs.ITmath.IT
收藏

字典学习ITKM算法的收敛半径和样本复杂度

Convergence radius and sample complexity of ITKM algorithms for dictionary learning

University of Innsbruck(因斯布鲁克大学)

Karin Schnass

摘要:

在这项工作中,我们表明,迭代阈值和K-均值(ITKM)算法可以恢复生成字典K原子从嘈杂的$S$稀疏信号的错误$\tilde \varepsilon$,只要初始化是在收敛半径内,这是一个$\log K$因子成反比的信号的动态范围,和样本大小成正比于$K \log K \tilde \varepsilon^{-2}$。结果是有效的任意目标误差,如果稀疏水平的信号尺寸$d$的平方根的顺序和目标误差下降到$K^{-\ell}$,如果$S$规模为$S \leq d/(\ell \log K)$。

英文摘要:

In this work we show that iterative thresholding and K-means (ITKM) algorithms can recover a generating dictionary with K atoms from noisy $S$ sparse signals up to an error $\tilde \varepsilon$ as long as the initialisation is within a convergence radius, that is up to a $\log K$ factor inversely proportional to the dynamic range of the signals, and the sample size is proportional to $K \log K \tilde \varepsilon^{-2}$. The results are valid for arbitrary target errors if the sparsity level is of the order of the square root of the signal dimension $d$ and for target errors down to $K^{-\ell}$ if $S$ scales as $S \leq d/(\ell \log K)$.

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。

↑