Journal article

A convex model for nonnegative matrix factorization and dimensionality reduction on physical space

Esser E, M??ller M, Osher S, Sapiro G, Xin J ...see all

IEEE Transactions on Image Processing, vol. 21, issue 7 (2012) pp. 3239-3252

  • 69


    Mendeley users who have this article in their library.
  • 65


    Citations of this article.
Sign in to save reference


A collaborative convex framework for factoring a data matrix $X$ into a non-negative product $AS$, with a sparse coefficient matrix $S$, is proposed. We restrict the columns of the dictionary matrix $A$ to coincide with certain columns of the data matrix $X$, thereby guaranteeing a physically meaningful dictionary and dimensionality reduction. We use $l_{1,\infty}$ regularization to select the dictionary from the data and show this leads to an exact convex relaxation of $l_0$ in the case of distinct noise free data. We also show how to relax the restriction-to-$X$ constraint by initializing an alternating minimization approach with the solution of the convex model, obtaining a dictionary close to but not necessarily in $X$. We focus on applications of the proposed framework to hyperspectral endmember and abundances identification and also show an application to blind source separation of NMR data.

Author-supplied keywords

  • Blind source separation (BSS)
  • dictionary learning
  • dimensionality reduction
  • hyperspectral endmember detection
  • nonnegative matrix factorization (NMF)
  • subset selection

Get free article suggestions today

Mendeley saves you time finding and organizing research

Sign up here
Already have an account ?Sign in

Find this document

Get full text


  • Ernie Esser

  • Michael M??ller

  • Stanley Osher

  • Guillermo Sapiro

  • Jack Xin

Cite this document

Choose a citation style from the tabs below

Save time finding and organizing research with Mendeley

Sign up for free