A note on the statistical view of matrix completion
Machine Learning
2016-05-11 v1
Abstract
A very simple interpretation of matrix completion problem is introduced based on statistical models. Combined with the well-known results from missing data analysis, such interpretation indicates that matrix completion is still a valid and principled estimation procedure even without the missing completely at random (MCAR) assumption, which almost all of the current theoretical studies of matrix completion assume.
Keywords
Cite
@article{arxiv.1605.03040,
title = {A note on the statistical view of matrix completion},
author = {Tianxi Li},
journal= {arXiv preprint arXiv:1605.03040},
year = {2016}
}