Tail sums of Wishart and GUE eigenvalues beyond the bulk edge
Iain M. Johnstone

TL;DR
This paper provides quantitative bounds on the tail sums of eigenvalues beyond the bulk edge for Wishart and GUE ensembles, with implications for high-dimensional covariance matrix estimation.
Contribution
It introduces new bounds on eigenvalue tail sums outside the bulk edge for Wishart and GUE ensembles, aiding high-dimensional covariance analysis.
Findings
Expected number of eigenvalues outside the bulk edge is less than one.
Tail sums of eigenvalues are quantitatively bounded.
Results are independent of the aspect ratio in the Wishart case.
Abstract
Consider the classical Gaussian unitary ensemble of size and the real Wishart ensemble . In the limits as and , the expected number of eigenvalues that exit the upper bulk edge is less than one, 0.031 and 0.170 respectively, the latter number being independent of . These statements are consequences of quantitative bounds on tail sums of eigenvalues outside the bulk which are established here for applications in high dimensional covariance matrix estimation.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsRandom Matrices and Applications · Bayesian Methods and Mixture Models · Statistical Methods and Inference
