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

A mix of human-written and AI-generated textHuman understanding: all partsmath.PR — Probabilitymath.ST — Statistics Theory

Contributed by Samuil Petkov ↗

Version 1 / Nov 19, 2026 / CC BY 4.0

Abstract

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.

Provenance statement

OpenAI GPT-5.6 Sol, accessed through ChatGPT and Codex, was used to develop the reduction, the numerical checks and the first draft. Anthropic Claude Opus 5.5, used through Claude Code, was used to merge and edit the note and to write the conditioning argument of Section 4, including the ratio lemma. It also produced the right-edge lemma, the paragraph that replaces the unverified part of Theorem 2.9 of Ben Arous et al. by Theorem 3.16 of Knowles and Yin for the outlier assertions, and the two-class numerical check. The author reviewed and takes responsibility for every statement and proof.

Tools used

OpenAI
ChatGPTVersion GPT-5.6 Sol
OpenAI
CodexVersion GPT-5.6 Sol
Anthropic
Claude CodeVersion Claude Opus 5.5

References

  1. Z. D. Bai and Jack W. Silverstein, No eigenvalues outside the support of the limiting spectral distribution of large-dimensional sample covariance matrices , Annals of Probability 26 (1998), no. 1, 316--345.
  2. Jinho Baik, G é rard Ben Arous, and Sandrine P é ch é , Phase transition of the largest eigenvalue for nonnull complex sample covariance matrices , Annals of Probability 33 (2005), no. 5, 1643--1697.
  3. G é rard Ben Arous, Reza Gheissari, Jiaoyang Huang, and Aukosh Jagannath, Local geometry of high-dimensional mixture models: Effective spectral theory and dynamical transitions , 2025, arXiv:2502.15655, version 3 (22 January 2026).arXiv
  4. Florent Benaych-Georges and Raj Rao Nadakuditi, The eigenvalues and eigenvectors of finite, low rank perturbations of large random matrices , Advances in Mathematics 227 (2011), no. 1, 494--521.
  5. Zhou Fan, Renyuan Ma, Elliot Paquette, and Zhichao Wang, Anisotropic local law for non-separable sample covariance matrices , 2026, arXiv:2602.17960.arXiv
  6. Antti Knowles and Jun Yin, Anisotropic local laws for random matrices , Probability Theory and Related Fields 169 (2017), no. 1-2, 257--352, arXiv:1410.3516; statement numbers as in the arXiv version.arXiv
  7. Filip Kova č evi ć , Yihan Zhang, and Marco Mondelli, Spectral estimators for multi-index models: Precise asymptotics and optimal weak recovery , Proceedings of Thirty Eighth Conference on Learning Theory, Proceedings of Machine Learning Research, vol. 291, PMLR, 2025, https://proceedings.mlr.press/v291/kovacevic25a.html, pp. 3354--3404.link
  8. V. A. Mar č enko and L. A. Pastur, Distribution of eigenvalues for some sets of random matrices , Mathematics of the USSR-Sbornik 1 (1967), no. 4, 457--483.
  9. Andrea Montanari and Basil Saeed, Variational formulas for the spectrum of block W ishart matrices , 2026, arXiv:2606.27774.arXiv
  10. Vinod Nair and Geoffrey E. Hinton, Rectified linear units improve restricted B oltzmann machines , Proceedings of the 27th International Conference on Machine Learning (Haifa, Israel), 2010.
Show all 11 referencesShow fewer references
  1. Jack W. Silverstein and Sang-Il Choi, Analysis of the limiting spectral distribution of large dimensional random matrices , Journal of Multivariate Analysis 54 (1995), no. 2, 295--309.

Version history

  1. v1 · 17 pagesSubmitted by Samuil PetkovInitial depositCurrentNov 19, 2026