A Generalized Divergence Measure for Nonnegative Matrix Factorization

@article{Kompass2007AGD,
  title={A Generalized Divergence Measure for Nonnegative Matrix Factorization},
  author={Raul Kompass},
  journal={Neural Computation},
  year={2007},
  volume={19},
  pages={780-791}
}
This letter presents a general parametric divergence measure. The metric includes as special cases quadratic error and Kullback-Leibler divergence. A parametric generalization of the two different multiplicative update rules for nonnegative matrix factorization by Lee and Seung (2001) is shown to lead to locally optimal solutions of the nonnegative matrix factorization problem with this new cost function. Numeric simulations demonstrate that the new update rule may improve the quadratic… CONTINUE READING
BETA

Similar Papers

Results and Topics from this paper.

Key Quantitative Results

  • An intermediate value of α = 12 was found to lead to costs of approximately 1.5% to 6% above the absolute minimum for both divergence measures, whereas the standard NMF updates, which correspond to α = 0 or α = 1, optimize one measure but lead to a 11% to 23% increase of the other.

Citations

Publications citing this paper.
SHOWING 1-10 OF 131 CITATIONS

Algorithms for Nonnegative Matrix Factorization with the β-Divergence

  • Neural Computation
  • 2011
VIEW 6 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Algorithms for nonnegative matrix factorization with the beta-divergence

VIEW 6 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

A Quasi-Likelihood Approach to Nonnegative Matrix Factorization

VIEW 6 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Learning the Information Divergence

  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • 2014
VIEW 7 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

FILTER CITATIONS BY YEAR

2006
2019

CITATION STATISTICS

  • 16 Highly Influenced Citations

References

Publications referenced by this paper.
SHOWING 1-7 OF 7 REFERENCES

Backpropagation Applied to Handwritten Zip Code Recognition

  • Neural Computation
  • 1989
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Neural Networks, Principal Components, and Subspaces

  • Int. J. Neural Syst.
  • 1989
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

CBCL face database #1

MIT center for biological, computation learning.
  • Available online at http://cbcl.mit.edu/cbcl/software-datasets/facedata2.html.
  • 2000