ABSTRACT
The problem of non-negative matrix factorization (NMF) is to express a non-negative matrix X of size m×n, either exactly or approximately, as a product of two non-negative matrices, W of size m× r and H of size r × n. Approximate NMF attempts to minimize a measure of divergence between the matrix X and the factorization WH. The inner dimension of the factorization r is usually taken to be much smaller than m and n to get interpretable part-based representation of data [22]. NMF is used in a wide range of applications, e.g., topic modeling and text mining, hyper-spectral image analysis, audio source separation, and microarray data analysis [7].
