Noisy low-rank matrix completion with general sampling distribution
Statistics Theory
2014-02-06 v3 Statistics Theory
Abstract
In the present paper, we consider the problem of matrix completion with noise. Unlike previous works, we consider quite general sampling distribution and we do not need to know or to estimate the variance of the noise. Two new nuclear-norm penalized estimators are proposed, one of them of "square-root" type. We analyse their performance under high-dimensional scaling and provide non-asymptotic bounds on the Frobenius norm error. Up to a logarithmic factor, these performance guarantees are minimax optimal in a number of circumstances.
Cite
@article{arxiv.1203.0108,
title = {Noisy low-rank matrix completion with general sampling distribution},
author = {Olga Klopp},
journal= {arXiv preprint arXiv:1203.0108},
year = {2014}
}
Comments
Published in at http://dx.doi.org/10.3150/12-BEJ486 the Bernoulli (http://isi.cbs.nl/bernoulli/) by the International Statistical Institute/Bernoulli Society (http://isi.cbs.nl/BS/bshome.htm)