Low rank matrix completion by alternating steepest descent methods

@inproceedings{Tanner2015LowRM,
  title={Low rank matrix completion by alternating steepest descent methods},
  author={Jared Tanner and Ke Wei},
  year={2015}
}
Matrix completion involves recovering a matrix from a subset of its entries by utilizing interdependency between the entries, typically through low rank structure. Despite matrix completion requiring the global solution of a non-convex objective, there are many computationally efficient algorithms which are effective for a broad class of matrices. In this paper, we introduce an alternating steepest descent algorithm (ASD) and a scaled variant, ScaledASD, for the fixedrank matrix completion… CONTINUE READING
Highly Cited
This paper has 35 citations. REVIEW CITATIONS

Citations

Publications citing this paper.
Showing 1-10 of 21 extracted citations

References

Publications referenced by this paper.

Similar Papers

Loading similar papers…