关于谱方法的局限性:从高斯隐团问题到高斯张量的秩一扰动
On the limitation of spectral methods: From the Gaussian hidden clique problem to rank one perturbations of Gaussian tensors
摘要:
我们考虑以下检测问题:给定一个实现的对称矩阵${\mathbf{X}}$的尺寸$n$,区分假设,所有上三角变量是独立同分布。具有均值0和方差$1$的高斯变量以及假设其中${\mathbf{X}}$是这样的矩阵和独立的秩一扰动的和。该设置适用于以下情况:在备选方案下,存在大小为$L$的种植主子矩阵${\mathbf{B}}$,其所有上三角变量均为i.i.d.。具有均值$1$和方差$1$的高斯分布,而不在${\mathbf{B}}$中的${\mathbf{X}}$的所有其他上三角元素都是独立同分布。均值为0且方差为$1$的高斯变量。我们将其称为“高斯隐藏集团问题”。当$L=(1+ε)\sqrt{n}$($ε>0$)时,可以通过计算${\mathbf{X}}$的频谱并考虑${\mathbf{X}}$的最大特征值来解决具有概率$1-o_n(1)$的该检测问题。我们证明了这个条件是紧在以下意义上:当$L<(1-ε)\sqrt{n}$没有算法,只检查${\mathbf{X}}$的特征值可以检测到一个隐藏的高斯团的存在,错误概率消失为$n\to\infty$。我们证明了这一结果作为一个更一般的结果秩一扰动$k$维高斯张量的直接后果。在这种情况下,我们建立了一个下限的临界信噪比低于一个秩一信号不能被检测到。
英文摘要:
We consider the following detection problem: given a realization of a symmetric matrix ${\mathbf{X}}$ of dimension $n$, distinguish between the hypothesis that all upper triangular variables are i.i.d. Gaussians variables with mean 0 and variance $1$ and the hypothesis where ${\mathbf{X}}$ is the sum of such matrix and an independent rank-one perturbation. This setup applies to the situation where under the alternative, there is a planted principal submatrix ${\mathbf{B}}$ of size $L$ for which all upper triangular variables are i.i.d. Gaussians with mean $1$ and variance $1$, whereas all other upper triangular elements of ${\mathbf{X}}$ not in ${\mathbf{B}}$ are i.i.d. Gaussians variables with mean 0 and variance $1$. We refer to this as the `Gaussian hidden clique problem.' When $L=(1+ε)\sqrt{n}$ ($ε>0$), it is possible to solve this detection problem with probability $1-o_n(1)$ by computing the spectrum of ${\mathbf{X}}$ and considering the largest eigenvalue of ${\mathbf{X}}$. We prove that this condition is tight in the following sense: when $L<(1-ε)\sqrt{n}$ no algorithm that examines only the eigenvalues of ${\mathbf{X}}$ can detect the existence of a hidden Gaussian clique, with error probability vanishing as $n\to\infty$. We prove this result as an immediate consequence of a more general result on rank-one perturbations of $k$-dimensional Gaussian tensors. In this context we establish a lower bound on the critical signal-to-noise ratio below which a rank-one signal cannot be detected.
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。