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

by Ernie Esser, Michael Möller, Stanley Osher, Guillermo Sapiro, Jack Xin
IEEE Transactions on Image Processing ()


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.

Cite this document (BETA)

Readership Statistics

45 Readers on Mendeley
by Discipline
by Academic Status
38% Ph.D. Student
13% Post Doc
11% Student (Master)
by Country
13% United States
2% France
2% China

Sign up today - FREE

Mendeley saves you time finding and organizing research. Learn more

  • All your research in one place
  • Add and import papers easily
  • Access it anywhere, anytime

Start using Mendeley in seconds!

Sign up & Download

Already have an account? Sign in