On -divergence based nonnegative matrix factorization for clustering cancer gene expression data

SummaryObjective ative matrix factorization (NMF) has been proven to be a powerful clustering method. Recently Cichocki and coauthors have proposed a family of new algorithms based on the α -divergence for NMF. However, it is an open problem to choose an optimal α . s and materials s paper, we tested such NMF variant with different α values on clustering cancer gene expression data for optimal α selection experimentally with 11 datasets. s and conclusion perimental results show that α = 1 and 2 are two special optimal cases for real applications.