High Dimensional Matrix Estimation With Unknown Variance Of The Noise
We propose a new pivotal method for estimating high-dimensional matrices. Assume that we observe a small set of entries or linear combinations of entries of an unknown matrix A0 corrupted by noise. We propose a new method for estimating A0 which does not rely on the knowledge or an estimation of the standard deviation of the noise . Our estimator achieves, up to a logarithmic factor, optimal rates of convergence under the Frobenius risk and, thus, has the same prediction performance as previously proposed estimators which rely on the knowledge of . Our method is based on the solution of a convex optimization problem which makes it computationally attractive
|Date of creation:||Feb 2012|
|Contact details of provider:|| Postal: Bâtiment ENSAE, 5 rue Henry LE Chatelier, 91120 Palaiseau|
Phone: 01 41 17 60 81
Web page: http://crest.science
More information through EDIRC
Please report citation or reference errors to , or , if you are the registered author of the cited work, log in to your RePEc Author Service profile, click on "citations" and make appropriate adjustments.:
- Angelika Rohde & Alexandre Tsybakov, 2010. "Estimation on High-dimensional Low Rank Matrices," Working Papers 2010-25, Center for Research in Economics and Statistics.
When requesting a correction, please mention this item's handle: RePEc:crs:wpaper:2012-05. See general information about how to correct material in RePEc.
For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: (Sri Srikandan)
If references are entirely missing, you can add them using this form.