A hybrid algorithm for non-negative matrix factorization based on symmetric information divergence

Karthik Devarajan, Nader Ebrahimi, Ehsan Soofi

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

4 Scopus citations

Abstract

The objective of this paper is to provide a hybrid algorithm for non-negative matrix factorization based on a symmetric version of Kullback-Leibler divergence, known as intrinsic information. The convergence of the proposed algorithm is shown for several members of the exponential family such as the Gaussian, Poisson, gamma and inverse Gaussian models. The speed of this algorithm is examined and its usefulness is illustrated through some applied problems.

Original languageEnglish
Title of host publicationProceedings - 2015 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2015
Editorslng. Matthieu Schapranow, Jiayu Zhou, Xiaohua Tony Hu, Bin Ma, Sanguthevar Rajasekaran, Satoru Miyano, Illhoi Yoo, Brian Pierce, Amarda Shehu, Vijay K. Gombar, Brian Chen, Vinay Pai, Jun Huan
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1658-1664
Number of pages7
ISBN (Electronic)9781467367981
DOIs
StatePublished - Dec 16 2015
Externally publishedYes
EventIEEE International Conference on Bioinformatics and Biomedicine, BIBM 2015 - Washington, United States
Duration: Nov 9 2015Nov 12 2015

Publication series

NameProceedings - 2015 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2015

Conference

ConferenceIEEE International Conference on Bioinformatics and Biomedicine, BIBM 2015
Country/TerritoryUnited States
CityWashington
Period11/9/1511/12/15

Keywords

  • Kullback-Leibler divergence
  • dual
  • exponential family
  • intrinsic information
  • non-negative matrix factorization

Fingerprint

Dive into the research topics of 'A hybrid algorithm for non-negative matrix factorization based on symmetric information divergence'. Together they form a unique fingerprint.

Cite this