Recovering low-rank matrices from few coefficients in any basis

Details Recovering low-rank matrices from few coefficients in any basis Recovering low-rank matrices from few coefficients in any basis

2009-10-12

arxiv.org/abs/0910.1879v5

IEEE Trans. on Information Theory, vol. 57, pages 1548 - 1566 (2011)

Computer Science

Information Theory

See also arxiv:0909.3304. v1=v2. v3: Some bounds substantially improved. v4, v5: presentation improved. To appear in IEEE Tran

Scientific paper

10.1109/TIT.2011.2104999

We present novel techniques for analyzing the problem of low-rank matrix recovery. The methods are both considerably simpler and more general than previous approaches. It is shown that an unknown (n x n) matrix of rank r can be efficiently reconstructed from only O(n r nu log^2 n) randomly sampled expansion coefficients with respect to any given matrix basis. The number nu quantifies the "degree of incoherence" between the unknown matrix and the basis. Existing work concentrated mostly on the problem of "matrix completion" where one aims to recover a low-rank matrix from randomly selected matrix elements. Our result covers this situation as a special case. The proof consists of a series of relatively elementary steps, which stands in contrast to the highly involved methods previously employed to obtain comparable results. In cases where bounds had been known before, our estimates are slightly tighter. We discuss operator bases which are incoherent to all low-rank matrices simultaneously. For these bases, we show that O(n r nu log n) randomly sampled expansion coefficients suffice to recover any low-rank matrix with high probability. The latter bound is tight up to multiplicative constants.

Affiliated with

Also associated with

No associations

Rating

Recovering low-rank matrices from few coefficients in any basis does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Recovering low-rank matrices from few coefficients in any basis, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Recovering low-rank matrices from few coefficients in any basis will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-463710