Optimal Recovery of Missing Values for Non-Negative Matrix Factorization: A Probabilistic Error Bound
Abstract
Missing values imputation is often evaluated on some similarity measure between actual and imputed data. However, it may be more meaningful to evaluate downstream algorithm performance after imputation than the imputation itself. We describe a straightforward unsupervised imputation algorithm, a minimax approach based on optimal recovery, and derive probabilistic error bounds on downstream non-negative matrix factorization (NMF). We also comment on fair imputation.
Cite
Text
Chen and Varshney. "Optimal Recovery of Missing Values for Non-Negative Matrix Factorization: A Probabilistic Error Bound." ICML 2020 Workshops: Artemiss, 2020.Markdown
[Chen and Varshney. "Optimal Recovery of Missing Values for Non-Negative Matrix Factorization: A Probabilistic Error Bound." ICML 2020 Workshops: Artemiss, 2020.](https://mlanthology.org/icmlw/2020/chen2020icmlw-optimal/)BibTeX
@inproceedings{chen2020icmlw-optimal,
title = {{Optimal Recovery of Missing Values for Non-Negative Matrix Factorization: A Probabilistic Error Bound}},
author = {Chen, Rebecca and Varshney, Lav R.},
booktitle = {ICML 2020 Workshops: Artemiss},
year = {2020},
url = {https://mlanthology.org/icmlw/2020/chen2020icmlw-optimal/}
}