English

Recover the spectrum of covariance matrix: a non-asymptotic iterative method

Machine Learning 2022-01-04 v1 Machine Learning Computation

Abstract

It is well known the sample covariance has a consistent bias in the spectrum, for example spectrum of Wishart matrix follows the Marchenko-Pastur law. We in this work introduce an iterative algorithm 'Concent' that actively eliminate this bias and recover the true spectrum for small and moderate dimensions.

Keywords

Cite

@article{arxiv.2201.00230,
  title  = {Recover the spectrum of covariance matrix: a non-asymptotic iterative method},
  author = {Juntao Duan and Ionel Popescu and Heinrich Matzinger},
  journal= {arXiv preprint arXiv:2201.00230},
  year   = {2022}
}