English

Convex Algorithms for Nonnegative Matrix Factorization

Optimization and Control 2012-07-03 v1

Abstract

We derive approximation algorithms for the nonnegative matrix factorization problem, i.e. the problem of factorizing a matrix as the product of two matrices with nonnegative coefficients. We form convex approximations of this problem which can be solved efficiently and test our algorithms on some classic numerical examples.

Keywords

Cite

@article{arxiv.1207.0318,
  title  = {Convex Algorithms for Nonnegative Matrix Factorization},
  author = {Vijay Krishnamurthy and Alexandre d'Aspremont},
  journal= {arXiv preprint arXiv:1207.0318},
  year   = {2012}
}

Comments

Discussion paper. Rejected by NIPS in 2007

R2 v1 2026-06-21T21:29:00.051Z