Information Theoretic Limits for Linear Prediction with Graph-Structured Sparsity
Machine Learning
2018-11-19 v2 Information Theory
math.IT
Machine Learning
Abstract
We analyze the necessary number of samples for sparse vector recovery in a noisy linear prediction setup. This model includes problems such as linear regression and classification. We focus on structured graph models. In particular, we prove that sufficient number of samples for the weighted graph model proposed by Hegde and others is also necessary. We use the Fano's inequality on well constructed ensembles as our main tool in establishing information theoretic lower bounds.
Cite
@article{arxiv.1701.07895,
title = {Information Theoretic Limits for Linear Prediction with Graph-Structured Sparsity},
author = {Adarsh Barik and Jean Honorio and Mohit Tawarmalani},
journal= {arXiv preprint arXiv:1701.07895},
year = {2018}
}