The Spectral Norm of Random Inner-Product Kernel Matrices
arXiv:1507.05343
Abstract
We study an "inner-product kernel" random matrix model, whose empirical spectral distribution was shown by Xiuyuan Cheng and Amit Singer to converge to a deterministic measure in the large and limit. We provide an interpretation of this limit measure as the additive free convolution of a semicircle law and a Marcenko-Pastur law. By comparing the tracial moments of this random matrix to those of a deformed GUE matrix with the same limiting spectrum, we establish that for odd kernel functions, the spectral norm of this matrix convergences almost surely to the edge of the limiting spectrum. Our study is motivated by the analysis of a covariance thresholding procedure for the statistical detection and estimation of sparse principal components, and our results characterize the limit of the largest eigenvalue of the thresholded sample covariance matrix in the null setting.
arXiv commentThis revision clarifies the proofs and statistical motivation
References in corpus (8)
- Sparse principal component analysis and iterative thresholding
- Optimal detection of sparse principal components in high dimension
- Sparse Principal Components Analysis
- Universality of covariance matrices
- Asymptotic power of sphericity tests for high-dimensional data
- Edge Universality for Deformed Wigner Matrices
- Bulk universality for deformed Wigner matrices
- On the convergence of the extremal eigenvalues of empirical covariance matrices with dependence