Bayes optimal learning in high-dimensional linear regression with network side information

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Nandy, Sagnik, Sen, Subhabrata
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909359278129152
author Nandy, Sagnik
Sen, Subhabrata
author_facet Nandy, Sagnik
Sen, Subhabrata
contents Supervised learning problems with side information in the form of a network arise frequently in applications in genomics, proteomics and neuroscience. For example, in genetic applications, the network side information can accurately capture background biological information on the intricate relations among the relevant genes. In this paper, we initiate a study of Bayes optimal learning in high-dimensional linear regression with network side information. To this end, we first introduce a simple generative model (called the Reg-Graph model) which posits a joint distribution for the supervised data and the observed network through a common set of latent parameters. Next, we introduce an iterative algorithm based on Approximate Message Passing (AMP) which is provably Bayes optimal under very general conditions. In addition, we characterize the limiting mutual information between the latent signal and the data observed, and thus precisely quantify the statistical impact of the network side information. Finally, supporting numerical experiments suggest that the introduced algorithm has excellent performance in finite samples.
format Preprint
id arxiv_https___arxiv_org_abs_2306_05679
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Bayes optimal learning in high-dimensional linear regression with network side information
Nandy, Sagnik
Sen, Subhabrata
Statistics Theory
Machine Learning
Supervised learning problems with side information in the form of a network arise frequently in applications in genomics, proteomics and neuroscience. For example, in genetic applications, the network side information can accurately capture background biological information on the intricate relations among the relevant genes. In this paper, we initiate a study of Bayes optimal learning in high-dimensional linear regression with network side information. To this end, we first introduce a simple generative model (called the Reg-Graph model) which posits a joint distribution for the supervised data and the observed network through a common set of latent parameters. Next, we introduce an iterative algorithm based on Approximate Message Passing (AMP) which is provably Bayes optimal under very general conditions. In addition, we characterize the limiting mutual information between the latent signal and the data observed, and thus precisely quantify the statistical impact of the network side information. Finally, supporting numerical experiments suggest that the introduced algorithm has excellent performance in finite samples.
title Bayes optimal learning in high-dimensional linear regression with network side information
topic Statistics Theory
Machine Learning
url https://arxiv.org/abs/2306.05679