Skip to yearly menu bar Skip to main content


Poster

Spectral Phase Transition and Optimal PCA in Block-Structured Spiked Models

Pierre Mergny · Justin Ko · FLORENT KRZAKALA

Hall C 4-9 #2616
[ ] [ Paper PDF ]
[ Poster
Wed 24 Jul 2:30 a.m. PDT — 4 a.m. PDT

Abstract:

We discuss the inhomogeneous Wigner spike model, a theoretical framework recently introduced to study structured noise in various learning scenarios, through the prism of random matrix theory, with a specific focus on its spectral properties. Our primary objective is to find an optimal spectral method, and to extend the celebrated (BBP) phase transition criterion ---well-known in the homogeneous case--- to our inhomogeneous, block-structured, Wigner model. We provide a thorough rigorous analysis of a transformed matrix and show that the transition for the appearance of 1) an outlier outside the bulk of the limiting spectral distribution and 2) a positive overlap between the associated eigenvector and the signal, occurs precisely at the optimal threshold, making the proposed spectral method optimal within the class of iterative methods for the inhomogeneous Wigner problem.

Chat is not available.