mlsanityData to 13 Oct 2026

A Non-Negative Matrix Factorization Game

arXiv 2104.05069 ↗First posted 11 Apr 2021cs.GT cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 13 Oct 2026). Builds on 3 of its 18 references that are in the map. First posted on arXiv 11 Apr 2021.

Builds on

3 of 18 references.

References · 3

  1. 2020EigenGame: PCA as a Nash Equilibriumcited by 39
  2. 2021EigenGame Unloaded: When playing games is better than optimizingcited by 13
  3. 2018Accelerating Nonnegative Matrix Factorization Algorithms using Extrapolationcited by 10

Built on by

Not cited yet.