Weighted matrix completion from non-random, non-uniform sampling patterns
Information Theory
2019-10-31 v1 math.IT
Statistics Theory
Statistics Theory
Abstract
We study the matrix completion problem when the observation pattern is deterministic and possibly non-uniform. We propose a simple and efficient debiased projection scheme for recovery from noisy observations and analyze the error under a suitable weighted metric. We introduce a simple function of the weight matrix and the sampling pattern that governs the accuracy of the recovered matrix. We derive theoretical guarantees that upper bound the recovery error and nearly matching lower bounds that showcase optimality in several regimes. Our numerical experiments demonstrate the computational efficiency and accuracy of our approach, and show that debiasing is essential when using non-uniform sampling patterns.
Cite
@article{arxiv.1910.13986,
title = {Weighted matrix completion from non-random, non-uniform sampling patterns},
author = {Simon Foucart and Deanna Needell and Reese Pathak and Yaniv Plan and Mary Wootters},
journal= {arXiv preprint arXiv:1910.13986},
year = {2019}
}
Comments
41 pages, 4 figures