Marchenko-Pastur law with relaxed independence conditions

Abstract

We prove the Marchenko-Pastur law for the eigenvalues of $p\times p$ sample covariance matrices in two new situations where the data does not have independent coordinates. In the first scenario - the block-independent model - the $p$ coordinates of the data are partitioned into blocks in such a way that the entries in different blocks are independent, but the entries from the same block may be dependent. In the second scenario - the random tensor model - the data is the homogeneous random tensor of order $d$, i.e. the coordinates of the data are all $\left(\genfrac{}{}{0ex}{}{n}{d}\right)$ different products of $d$ variables chosen from a set of $n$ independent random variables. We show that Marchenko-Pastur law holds for the block-independent model as long as the size of the largest block is $o(p)$ and for the random tensor model as long as $d=o(n^{1/3})$. Our main technical tools are new concentration inequalities for quadratic forms in random variables with block-independent coordinates, and for random tensors.

arXiv comment23 pages, 4 figures

References in corpus (7)

• A Random Matrix Approach to Cross-Correlations in Financial Data
• Estimates of moments and tails of Gaussian chaoses
• Consistency of Spectral Hypergraph Partitioning under Planted Partition Model
• Fast and Guaranteed Tensor Decomposition via Sketching
• A short proof of the Marchenko-Pastur theorem
• Tail and moment estimates for chaoses generated by symmetric random variables with logarithmically concave tails
• Moments of the Gaussian Chaos

Cited by in corpus (2)

• Landscape analysis of an improved power method for tensor decomposition
• How many samples are needed to reliably approximate the best linear estimator for a linear inverse problem?