Matching works

1 work

math.PR — Probability

Spectral outliers of self-coupled covariance matrices with exact zero weights

Contributed by Samuil Petkov

We study the right spectral outliers of Md=n−1AdDAdTM_d=n^{-1}A_dDA_d^{\mathsf T}, where the columns of AdA_d are drawn from a Gaussian mixture with a fixed-dimensional signal subspace and each diagonal weight Dℓℓ=hbℓ(gℓ)D_{\ell\ell}=h_{b_\ell}(g_\ell) is a function of the class label and of the low-dimensional Gaussian coordinates of the same sample. The effective outlier theory of Ben Arous, Gheissari, Huang and Jagannath for such self-coupled matrices assumes that the weights do not accumulate at zero, which excludes hard gates such as the derivative of a rectified linear unit. Assuming hb(g)∈{0}∪[τ,M]h_b(g)\in\{0\}\cup[\tau,M], we prove that exact zero weights do not change the positive right-outlier equation. The proof deletes inactive columns before any linearization, keeps their random normalization, and applies the invertible-weight theory to the exact conditional mark law of the active samples; we show, by conditioning on the marks, that this theory extends to non-Gaussian fixed-dimensional marks. The limiting spectrum acquires the atom (1−ϕπ)+(1-\phi\pi)_+ at zero, while positive outliers are the roots of a q×qq\times q determinant. We obtain multiplicity-preserving eigenvalue counts, absence of spurious right outliers, a projected-eigenvector normalization, an invariant-subspace formula at repeated roots, and the exact finite-dimensional kernel.

A mix of human-written and AI-generated textHuman understanding: all partsGaussian mixturesexact zero weightsrandom matricesrectified linear unitspectral outliersweighted sample covariance matrices
Nov 19, 202617 pages
PDFView work

Advanced search

Text
Human understanding
Linked formalizations