Sciweavers

JMLR
2012

Primal-Dual methods for sparse constrained matrix completion

12 years 1 months ago
Primal-Dual methods for sparse constrained matrix completion
We develop scalable algorithms for regular and non-negative matrix completion. In particular, we base the methods on trace-norm regularization that induces a low rank predicted matrix. The regularization problem is solved via a constraint generation method that explicitly maintains a sparse dual and the corresponding low rank primal solution. We provide a new dual block coordinate descent algorithm for solving the dual problem with a few spectral constraints. Empirical results illustrate the effectiveness of our method in comparison to recently proposed alternatives.
Yu Xin, Tommi Jaakkola
Added 27 Sep 2012
Updated 27 Sep 2012
Type Journal
Year 2012
Where JMLR
Authors Yu Xin, Tommi Jaakkola
Comments (0)