Denoising Linear Models with Permuted Data
Machine Learning
2017-04-26 v1 Information Theory
math.IT
Statistics Theory
Statistics Theory
Abstract
The multivariate linear regression model with shuffled data and additive Gaussian noise arises in various correspondence estimation and matching problems. Focusing on the denoising aspect of this problem, we provide a characterization the minimax error rate that is sharp up to logarithmic factors. We also analyze the performance of two versions of a computationally efficient estimator, and establish their consistency for a large range of input parameters. Finally, we provide an exact algorithm for the noiseless problem and demonstrate its performance on an image point-cloud matching task. Our analysis also extends to datasets with outliers.
Keywords
Cite
@article{arxiv.1704.07461,
title = {Denoising Linear Models with Permuted Data},
author = {Ashwin Pananjady and Martin J. Wainwright and Thomas A. Courtade},
journal= {arXiv preprint arXiv:1704.07461},
year = {2017}
}
Comments
To appear in part at ISIT 2017, Aachen