Spectral Estimators for Structured Generalized Linear Models via Approximate Message Passing

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Yihan, Ji, Hong Chang, Venkataramanan, Ramji, Mondelli, Marco
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908442540638208
author Zhang, Yihan
Ji, Hong Chang
Venkataramanan, Ramji
Mondelli, Marco
author_facet Zhang, Yihan
Ji, Hong Chang
Venkataramanan, Ramji
Mondelli, Marco
contents We consider the problem of parameter estimation in a high-dimensional generalized linear model. Spectral methods obtained via the principal eigenvector of a suitable data-dependent matrix provide a simple yet surprisingly effective solution. However, despite their wide use, a rigorous performance characterization, as well as a principled way to preprocess the data, are available only for unstructured (i.i.d.\ Gaussian and Haar orthogonal) designs. In contrast, real-world data matrices are highly structured and exhibit non-trivial correlations. To address the problem, we consider correlated Gaussian designs capturing the anisotropic nature of the features via a covariance matrix $Σ$. Our main result is a precise asymptotic characterization of the performance of spectral estimators. This allows us to identify the optimal preprocessing that minimizes the number of samples needed for parameter estimation. Surprisingly, such preprocessing is universal across a broad set of designs, which partly addresses a conjecture on optimal spectral estimators for rotationally invariant models. Our principled approach vastly improves upon previous heuristic methods, including for designs common in computational imaging and genetics. The proposed methodology, based on approximate message passing, is broadly applicable and opens the way to the precise characterization of spiked matrices and of the corresponding spectral methods in a variety of settings.
format Preprint
id arxiv_https___arxiv_org_abs_2308_14507
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Spectral Estimators for Structured Generalized Linear Models via Approximate Message Passing
Zhang, Yihan
Ji, Hong Chang
Venkataramanan, Ramji
Mondelli, Marco
Statistics Theory
Information Theory
Machine Learning
Probability
We consider the problem of parameter estimation in a high-dimensional generalized linear model. Spectral methods obtained via the principal eigenvector of a suitable data-dependent matrix provide a simple yet surprisingly effective solution. However, despite their wide use, a rigorous performance characterization, as well as a principled way to preprocess the data, are available only for unstructured (i.i.d.\ Gaussian and Haar orthogonal) designs. In contrast, real-world data matrices are highly structured and exhibit non-trivial correlations. To address the problem, we consider correlated Gaussian designs capturing the anisotropic nature of the features via a covariance matrix $Σ$. Our main result is a precise asymptotic characterization of the performance of spectral estimators. This allows us to identify the optimal preprocessing that minimizes the number of samples needed for parameter estimation. Surprisingly, such preprocessing is universal across a broad set of designs, which partly addresses a conjecture on optimal spectral estimators for rotationally invariant models. Our principled approach vastly improves upon previous heuristic methods, including for designs common in computational imaging and genetics. The proposed methodology, based on approximate message passing, is broadly applicable and opens the way to the precise characterization of spiked matrices and of the corresponding spectral methods in a variety of settings.
title Spectral Estimators for Structured Generalized Linear Models via Approximate Message Passing
topic Statistics Theory
Information Theory
Machine Learning
Probability
url https://arxiv.org/abs/2308.14507