A Non-Negative Matrix Factorization Game

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 (Lee & Seung, 1999) algorithm.

Cite

Text

Singh. "A Non-Negative Matrix Factorization Game." ICLR 2022 Workshops: GMS, 2022.

Markdown

[Singh. "A Non-Negative Matrix Factorization Game." ICLR 2022 Workshops: GMS, 2022.](https://mlanthology.org/iclrw/2022/singh2022iclrw-nonnegative/)

BibTeX

@inproceedings{singh2022iclrw-nonnegative,
  title     = {{A Non-Negative Matrix Factorization Game}},
  author    = {Singh, Satpreet Harcharan},
  booktitle = {ICLR 2022 Workshops: GMS},
  year      = {2022},
  url       = {https://mlanthology.org/iclrw/2022/singh2022iclrw-nonnegative/}
}