Saved in:
Bibliographic Details
Main Authors: Forner, Niklas, Maloney, Alexander, Rosenow, Bernd
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2511.18501
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909919894044672
author Forner, Niklas
Maloney, Alexander
Rosenow, Bernd
author_facet Forner, Niklas
Maloney, Alexander
Rosenow, Bernd
contents Random-matrix theory helps disentangle signal from noise in large data sets. We analyze rectangular $p \times q$ matrices $W = W_0 + M$ in which the noise $M$ generates a Marchenko-Pastur bulk, whereas the signal $W_0$ injects an extensive set of degenerate singular values. Keeping $\mathrm{rank}$ $W_0/q$ finite as $p,q \to \infty$, we show that the singular value density obeys a quartic equation and derive explicit asymptotics in the strong-signal regime. The resulting generalized Baik-Ben Arous-Péché phase diagram yields a scaling law for the critical signal strength and clarifies how a finite density of spikes reshapes the bulk edges. Numerical simulations validate the theory and illustrate its relevance for high-dimensional inference tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2511_18501
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle BBP Phase Transition for an Extensive Number of Outliers
Forner, Niklas
Maloney, Alexander
Rosenow, Bernd
Disordered Systems and Neural Networks
Random-matrix theory helps disentangle signal from noise in large data sets. We analyze rectangular $p \times q$ matrices $W = W_0 + M$ in which the noise $M$ generates a Marchenko-Pastur bulk, whereas the signal $W_0$ injects an extensive set of degenerate singular values. Keeping $\mathrm{rank}$ $W_0/q$ finite as $p,q \to \infty$, we show that the singular value density obeys a quartic equation and derive explicit asymptotics in the strong-signal regime. The resulting generalized Baik-Ben Arous-Péché phase diagram yields a scaling law for the critical signal strength and clarifies how a finite density of spikes reshapes the bulk edges. Numerical simulations validate the theory and illustrate its relevance for high-dimensional inference tasks.
title BBP Phase Transition for an Extensive Number of Outliers
topic Disordered Systems and Neural Networks
url https://arxiv.org/abs/2511.18501