A Non-Negative Matrix Factorization Game

Autor:	Singh, Satpreet H.
Rok vydání:	2021
Předmět:	Computer Science - Computer Science and Game Theory Computer Science - Machine Learning I.2.6 I.2.11
Druh dokumentu:	Working Paper
Popis:	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.
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2104.05069 Zobrazit plný text záznamu View this record from Arxiv