Sharp Information-Theoretic Thresholds for Shuffled Linear Regression
Abstract
This paper studies the problem of shuffled linear regression, where the correspondence between predictors and responses in a linear model is obfuscated by a latent permutation. Specifically, we consider the model , where is an standard Gaussian design matrix, is Gaussian noise with entrywise variance , is an unknown permutation matrix, and is the regression coefficient, also unknown. Previous work has shown that, in the large -limit, the minimal signal-to-noise ratio (), , for recovering the unknown permutation exactly with high probability is between and for some absolute constant and the sharp threshold is unknown even for . We show that this threshold is precisely for exact recovery throughout the sublinear regime . As a by-product of our analysis, we also determine the sharp threshold of almost exact recovery to be , where all but a vanishing fraction of the permutation is reconstructed.
Cite
@article{arxiv.2402.09693,
title = {Sharp Information-Theoretic Thresholds for Shuffled Linear Regression},
author = {Leon Lufkin and Yihong Wu and Jiaming Xu},
journal= {arXiv preprint arXiv:2402.09693},
year = {2024}
}
Comments
18 pages (9 main, 1 references, 8 appendix)