pith. sign in

arxiv: 1802.00381 · v2 · pith:WURVHALYnew · submitted 2018-02-01 · 🧮 math.ST · stat.TH

Signal-plus-noise matrix models: eigenvector deviations and fluctuations

classification 🧮 math.ST stat.TH
keywords matrixdeviationseigenvectorsfluctuationsmodelsrandomresultssignal-plus-noise
0
0 comments X
read the original abstract

Estimating eigenvectors and low-dimensional subspaces is of central importance for numerous problems in statistics, computer science, and applied mathematics. This paper characterizes the behavior of perturbed eigenvectors for a range of signal-plus-noise matrix models encountered in both statistical and random matrix theoretic settings. We prove both first-order approximation results (i.e. sharp deviations) as well as second-order distributional limit theory (i.e. fluctuations). The concise methodology considered in this paper synthesizes tools rooted in two core concepts, namely (i) deterministic decompositions of matrix perturbations and (ii) probabilistic matrix concentration phenomena. We illustrate our theoretical results via simulation examples involving stochastic block model random graphs.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.