English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
 
 
DownloadE-Mail
 Local TagsRelease HistoryDetailsSummary
  Block Iterative Algorithms for Non-negative Matrix Approximation

Sra, S. (2009). Block Iterative Algorithms for Non-negative Matrix Approximation. In F. Giannotti, D. Gunopulos, F. Turini, C. Zaniolo, N. Ramakrishnan, & X. Wu (Eds.), 2008 Eighth IEEE International Conference on Data Mining (pp. 1037-1042). Piscataway, NJ, USA: IEEE.

Item is

 

show all hide all

Basic

show hide
Item Permalink: https://hdl.handle.net/11858/00-001M-0000-0013-C62B-8 Version Permalink: https://hdl.handle.net/21.11116/0000-0003-3794-8
Genre: Conference Paper

Files

show Files

Locators

show
hide
Locator:
https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=4781221 (Publisher version)
Description:
-
OA-Status:

Creators

show
hide
 Creators:
Sra, S1, Author           
Affiliations:
1External Organizations, ou_persistent22              

Content

show
hide
Free keywords: -
 Abstract: In this paper we present new algorithms for non-negative matrix approximation (NMA), commonly known as the NMF problem. Our methods improve upon the well-known methods of Lee Seung~citelee00} for both the Frobenius norm as well the Kullback-Leibler divergence versions of the problem. For the latter problem, our results are especially interesting because it seems to have witnessed much lesser algorithmic progress as compared to the Frobenius norm NMA problem. Our algorithms are based on a particular textbf {block-iterative} acceleration technique for EM, which preserves the multiplicative nature of the updates and also ensures monotonicity. Furthermore, our algorithms also naturally apply to the Bregman-divergence NMA algorithms of~cite{suv.nips. Experimentally, we show that our algorithms outperform the traditional Lee/Seung approach most of the time.

Details

show
hide
Language(s):
 Dates: 2009-02
 Publication Status: Issued
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: DOI: 10.1109/ICDM.2008.77
BibTex Citekey: 5504
 Degree: -

Event

show
hide
Title: Eighth IEEE International Conference on Data Mining (ICDM 2008)
Place of Event: Pisa, Italy
Start-/End Date: 2008-12-15 - 2008-12-19

Legal Case

show

Project information

show

Source 1

show
hide
Title: 2008 Eighth IEEE International Conference on Data Mining
Source Genre: Proceedings
 Creator(s):
Giannotti, F, Editor
Gunopulos, D, Editor
Turini, F, Editor
Zaniolo, C, Editor
Ramakrishnan, N, Editor
Wu, X, Editor
Affiliations:
-
Publ. Info: Piscataway, NJ, USA : IEEE
Pages: - Volume / Issue: - Sequence Number: - Start / End Page: 1037 - 1042 Identifier: ISBN: 978-0-7695-3502-9