eigengap.oht {sgdGMF} | R Documentation |
Rank selection via optimal hard thresholding
Description
Select the number of significant principal components of a matrix via optimal hard thresholding (OHT)
Usage
eigengap.oht(covmat, nobs, maxcomp = NULL)
Arguments
covmat |
matrix to be decomposed |
nobs |
number of observations used to compute the covariance matrix |
maxcomp |
maximum number of eigenvalues to compute |
References
Gavish, M., Donoho, D.L. (2014) The optimal hard thresholding for singular values is 4/sqrt(3). IEEE Transactions on Information Theory, 60(8): 5040–5053
[Package sgdGMF version 1.0.1 Index]