Randomized Low-Memory Singular Value Projection

Affine rank minimization algorithms typically rely on calculating the gradient of a data error followed by a singular value decomposition at every iteration. Because these two steps are expensive, heuristics are often used for approximations that reduce computational burden. In this paper, we propose one recovery scheme that merges the two steps and show that it actually admits provable recovery guarantees while operating on space proportional to the degrees of freedom in the problem.


Presented at:
10th International Conference on Sampling Theory and Applications (Sampta), Bremen, Germany, July 1st - July 5th, 2013
Year:
2013
Keywords:
Laboratories:




 Record created 2013-02-25, last modified 2018-09-13

Preprint:
Download fulltext
PDF

Rate this document:

Rate this document:
1
2
3
 
(Not yet reviewed)