One-Way Matching of Datasets with Low Rank Signals
Statistics Theory
2022-10-04 v2 Information Theory
Machine Learning
math.IT
Quantitative Methods
Statistics Theory
Abstract
We study one-way matching of a pair of datasets with low rank signals. Under a stylized model, we first derive information-theoretic limits of matching under a mismatch proportion loss. We then show that linear assignment with projected data achieves fast rates of convergence and sometimes even minimax rate optimality for this task. The theoretical error bounds are corroborated by simulated examples. Furthermore, we illustrate practical use of the matching procedure on two single-cell data examples.
Cite
@article{arxiv.2204.13858,
title = {One-Way Matching of Datasets with Low Rank Signals},
author = {Shuxiao Chen and Sizun Jiang and Zongming Ma and Garry P. Nolan and Bokai Zhu},
journal= {arXiv preprint arXiv:2204.13858},
year = {2022}
}