High dimensional deformed rectangular matrices with applications in matrix denoising
arXiv:1702.06975
Abstract
We consider the recovery of a low rank matrix from its noisy observation in two different regimes. Under the assumption that is comparable to , we propose two consistent estimators for . Our analysis relies on the local behavior of the large dimensional rectangular matrices with finite rank perturbation. We also derive the convergent limits and rates for the singular values and vectors of such matrices.
References in corpus (5)
- Universality of covariance matrices
- The outliers of a deformed Wigner matrix
- Factor modeling for high-dimensional time series: Inference for the number of factors
- Estimation of the Number of Spikes, Possibly Equal, in the High-Dimensional Case
- Rate Optimal Denoising of Simultaneously Sparse and Low Rank Matrices