arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1202.3155math.PR
收藏

随机内积核矩阵的谱

The Spectrum of Random Inner-product Kernel Matrices

Xiuyuan Cheng, Amit Singer

摘要:

我们考虑第(i,j)项为f(X_i^T X_j)的n × n矩阵,其中X_1,.,X_n是i.i.d. R^p中的标准高斯随机向量,并且f是实值函数。在“大p,大n”的情况下研究了这些随机核矩阵的特征值分布。证明了当p和n趋于无穷大,p/n = γ为常数,且f适当标度使得Var(f(X_i^T X_j))为O(p^{-1})时,谱密度弱收敛到R上的极限密度.极限密度由涉及其斯蒂尔切斯变换的三次方程决定。虽然光滑的核函数的极限谱密度已被证明是Marcenko-Pastur分布,我们的分析是适用于非光滑的核函数,从而在一个新的家庭的极限密度。

英文摘要:

We consider n-by-n matrices whose (i, j)-th entry is f(X_i^T X_j), where X_1, ...,X_n are i.i.d. standard Gaussian random vectors in R^p, and f is a real-valued function. The eigenvalue distribution of these random kernel matrices is studied at the "large p, large n" regime. It is shown that, when p and n go to infinity, p/n = γwhich is a constant, and f is properly scaled so that Var(f(X_i^T X_j)) is O(p^{-1}), the spectral density converges weakly to a limiting density on R. The limiting density is dictated by a cubic equation involving its Stieltjes transform. While for smooth kernel functions the limiting spectral density has been previously shown to be the Marcenko-Pastur distribution, our analysis is applicable to non-smooth kernel functions, resulting in a new family of limiting densities.

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。

↑