Dyson Equation for Correlated Linearizations and Test Error of Random Features Regression

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Latourelle-Vigeant, Hugo, Paquette, Elliot
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917101057343488
author Latourelle-Vigeant, Hugo
Paquette, Elliot
author_facet Latourelle-Vigeant, Hugo
Paquette, Elliot
contents This paper develops some theory of the Dyson equation for correlated linearizations and uses it to solve a problem on asymptotic deterministic equivalent for the test error in random features regression. The theory developed for the correlated Dyson equation includes existence-uniqueness, spectral support bounds, and stability properties. This theory is new for constructing deterministic equivalents for pseudo-resolvents of a class of linearizations with correlated entries. In the application, this theory is used to give a deterministic equivalent of the test error in random features ridge regression, in a proportional scaling regime, wherein we have conditioned on both training and test datasets.
format Preprint
id arxiv_https___arxiv_org_abs_2312_09194
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Dyson Equation for Correlated Linearizations and Test Error of Random Features Regression
Latourelle-Vigeant, Hugo
Paquette, Elliot
Statistics Theory
Probability
This paper develops some theory of the Dyson equation for correlated linearizations and uses it to solve a problem on asymptotic deterministic equivalent for the test error in random features regression. The theory developed for the correlated Dyson equation includes existence-uniqueness, spectral support bounds, and stability properties. This theory is new for constructing deterministic equivalents for pseudo-resolvents of a class of linearizations with correlated entries. In the application, this theory is used to give a deterministic equivalent of the test error in random features ridge regression, in a proportional scaling regime, wherein we have conditioned on both training and test datasets.
title Dyson Equation for Correlated Linearizations and Test Error of Random Features Regression
topic Statistics Theory
Probability
url https://arxiv.org/abs/2312.09194