CX {ccTensor} | R Documentation |
The input data is assumed to be a matrix. CX decomposes the matrix to two low-dimensional factor matices. C is not an estimated values but the actual column vectors sampled from the matrix.
CX(A, rank=NULL, thr=0.9, c.method=c("best.match", "random", "exact.num.random", "top.scores"))
A |
The input matrix which has N-rows and M-columns. |
rank |
The number of low-dimension (J < N,M). If this argument is not specified or specified as NULL, the low-dimension is estimated based on the cumulative singular value (Default: NULL). |
thr |
The threshold to determine the low-dimension J. The value must be range 0 to 1 (Default: 0.9). |
c.method |
The column sampling algorithm (Default: best.match). |
C: A N-rows and J-columns matrix contains the sampled column vectors from the input matrix A. X: A J-rows and M-columns matrix. indC: The sampled column indices. RecError : The reconstruction error between data matrix and reconstructed matrix from C and X.
Koki Tsuyuzaki
Petros Drineas et.al., (2008). Relative-error CUR Matrix Decompositions. SIAM J. Matrix Anal. Appl.
library("ccTensor") library("nnTensor") # Test data matdata <- toyModel(model = "NMF") # Simple usage out <- CX(matdata, rank=5)