English

Two step recovery of jointly sparse and low-rank matrices: theoretical guarantees

Machine Learning 2015-06-03 v2 Information Theory math.IT

Abstract

We introduce a two step algorithm with theoretical guarantees to recover a jointly sparse and low-rank matrix from undersampled measurements of its columns. The algorithm first estimates the row subspace of the matrix using a set of common measurements of the columns. In the second step, the subspace aware recovery of the matrix is solved using a simple least square algorithm. The results are verified in the context of recovering CINE data from undersampled measurements; we obtain good recovery when the sampling conditions are satisfied.

Keywords

Cite

@article{arxiv.1412.2669,
  title  = {Two step recovery of jointly sparse and low-rank matrices: theoretical guarantees},
  author = {Sampurna Biswas and Sunrita Poddar and Soura Dasgupta and Raghuraman Mudumbai and Mathews Jacob},
  journal= {arXiv preprint arXiv:1412.2669},
  year   = {2015}
}

Comments

4 pages, 4 figures, ISBI 2015 conference submission