Precise Asymptotics for Spectral Methods in Mixed Generalized Linear Models

arXiv:2211.11368v3 Announce Type: replace-cross
Abstract: In a mixed generalized linear model, the objective is to learn multiple signals from unlabeled observations: each sample comes from exactly one signal, but it is not known which one. We consider the prototypical problem of estimating two statistically independent signals in a mixed generalized linear model with Gaussian covariates. Spectral methods are a popular class of estimators which output the top two eigenvectors of a suitable data-dependent matrix. However, despite the wide applicability, their …

abstract arxiv cs.it cs.lg generalized independent learn linear linear model math.it math.st mixed multiple sample signal stat.ml stat.th type