A Non-Negative Matrix Factorization Game
Computer Science and Game Theory
2021-04-13 v1 Machine Learning
Abstract
We present a novel game-theoretic formulation of Non-Negative Matrix Factorization (NNMF), a popular data-analysis method with many scientific and engineering applications. The game-theoretic formulation is shown to have favorable scaling and parallelization properties, while retaining reconstruction and convergence performance comparable to the traditional Multiplicative Updates algorithm.
Cite
@article{arxiv.2104.05069,
title = {A Non-Negative Matrix Factorization Game},
author = {Satpreet H. Singh},
journal= {arXiv preprint arXiv:2104.05069},
year = {2021}
}