Back
Sparse nonnegative matrix approximation: new formulations and algorithms
We introduce several new formulations for sparse nonnegative matrix approximation. Subsequently, we solve these formulations by developing generic algorithms. Further, to help selecting a particular sparse formulation, we briefly discuss the interpretation of each formulation. Finally, preliminary experiments are presented to illustrate the behavior of our formulations and algorithms.
@techreport{6764, title = {Sparse nonnegative matrix approximation: new formulations and algorithms}, abstract = {We introduce several new formulations for sparse nonnegative matrix approximation. Subsequently, we solve these formulations by developing generic algorithms. Further, to help selecting a particular sparse formulation, we briefly discuss the interpretation of each formulation. Finally, preliminary experiments are presented to illustrate the behavior of our formulations and algorithms.}, number = {193}, organization = {Max-Planck-Gesellschaft}, institution = {Max Planck Institute for Biological Cybernetics, Tübingen, Germany}, school = {Biologische Kybernetik}, month = sep, year = {2010}, slug = {6764}, author = {Tandon, R. and Sra, S.}, month_numeric = {9} }