Additive Non-negative Matrix Factorization for Missing Data
Numerical Analysis
2010-07-05 v1 Machine Learning
Abstract
Non-negative matrix factorization (NMF) has previously been shown to be a useful decomposition for multivariate data. We interpret the factorization in a new way and use it to generate missing attributes from test data. We provide a joint optimization scheme for the missing attributes as well as the NMF factors. We prove the monotonic convergence of our algorithms. We present classification results for cases with missing attributes.
Cite
@article{arxiv.1007.0380,
title = {Additive Non-negative Matrix Factorization for Missing Data},
author = {Mithun Das Gupta},
journal= {arXiv preprint arXiv:1007.0380},
year = {2010}
}
Comments
General extension of the NMF framework