analiza aiqbench
This research addresses a critical gap in spectral analysis by quantifying how heterogeneous noise distributions induce systematic geometric biases in eigenvectors that classical worst-case bounds miss. By leveraging the Quadratic Vector Equation (QVE) and isotropic local laws, the authors derive sharper, non-asymptotic guarantees essential for robust low-rank signal recovery in real-world noisy environments. These theoretical advances directly improve the consistency of adjacency spectral clustering and spectral embedding techniques used in graph neural networks and community detection.
Geometric bias in eigenspace perturbation under random heterogeneous noise
arXiv:2606.11263v2 Announce Type: replace-cross Abstract: Spectral methods rely on the stability of principal eigenspaces under random perturbations. Classically, this is quantified by the Davis-Kahan and Wedin theorems, which bound the eigenspace error via the operator norm of the noise and the relevant spectral gaps. While sharp for arbitrary deterministic perturbations, these worst-case bounds can be wasteful in the low-rank signal-plus-noise setting, as they fail to capture the interaction between the signal geometry and the noise distribution. We study the spectral perturbation of signal-plus-noise matrices corrupted by sparse random noise with an arbitrary, inhomogeneous variance profile. Under heterogeneous variances, the empirical eigenvectors suffer a systematic, deterministic geometric bias invisible to classical bounds. Leveraging the Quadratic Vector Equation (QVE) and fine-grained isotropic local laws, we derive near-optimal, non-asymptotic bounds for the leading eigenspaces in the operator and 2-to-infinity norms. These separate the usual signal-to-noise contribution, stochastic fluctuations, and structured geometric bias terms determined by the alignment between the signal eigenspaces and the row-wise variance profile. We further develop refined rowwise bounds that adapt to the variance-weighted leverage of the signal space, yielding sharper guarantees in delocalized regimes. As applications, we establish strong consistency of adjacency spectral clustering for degree-corrected stochastic block models with heterogeneous degrees and unbalanced communities, recovering the logarithmic expected-degree scale in the regular balanced case. We also study spectral embedding for generalized random dot product graphs, showing that the full signal embedding admits sharp rowwise control, whereas spectral truncation can retain a systematic geometric bias determined by the omitted signal directions and the variance profile.
Abstract:Spectral methods rely on the stability of principal eigenspaces under random perturbations. Classically, this is quantified by the Davis-Kahan and Wedin theorems, which bound the eigenspace error via the operator norm of the noise and the relevant spectral gaps. While sharp for arbitrary deterministic perturbations, these worst-case bounds can be wasteful in the low-rank signal-plus-noise setting, as they fail to capture the interaction between the signal geometry and the noise distribution. We study the spectral perturbation of signal-plus-noise matrices corrupted by sparse random noise with an arbitrary, inhomogeneous variance profile. Under heterogeneous variances, the empirical eigenvectors suffer a systematic, deterministic geometric bias invisible to classical bounds. Leveraging the Quadratic Vector Equation (QVE) and fine-grained isotropic local laws, we derive near-optimal, non-asymptotic bounds for the leading eigenspaces in the operator and 2-to-infinity norms. These separate the usual signal-to-noise contribution, stochastic fluctuations, and structured geometric bias terms determined by the alignment between the signal eigenspaces and the row-wise variance profile. We further develop refined rowwise bounds that adapt to the variance-weighted leverage of the signal space, yielding sharper guarantees in delocalized regimes. As applications, we establish strong consistency of adjacency spectral clustering for degree-corrected stochastic block models with heterogeneous degrees and unbalanced communities, recovering the logarithmic expected-degree scale in the regular balanced case. We also study spectral embedding for generalized random dot product graphs, showing that the full signal embedding admits sharp rowwise control, whereas spectral truncation can retain a systematic geometric bias determined by the omitted signal directions and the variance profile.
132 pages, 2 figures. Restructured the paper and added new applications of the main perturbation results
Statistics Theory (math.ST); Machine Learning (cs.LG); Numerical Analysis (math.NA); Probability (math.PR)
arXiv:2606.11263 [math.ST]
(or arXiv:2606.11263v2 [math.ST] for this version)
https://doi.org/10.48550/arXiv.2606.11263 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 367 cuvinte
Subiecte conexe
Geometric bias in eigenspace perturbation under random heterogeneous noise
arXiv · 12 iun. 2026
PIRAMID: Progress and Plans
LessWrong · 27 iul. 2026
SDFLoRA: Selective Decoupled Federated LoRA for Privacy-preserving Fine-tuning with Heterogeneous Clients
arXiv · 16 iun. 2026
Cumulant Framework Analyzes Quantum Noise Beyond Standard Models
Quantum Zeitgeist · 1 aug. 2026