k_unfold: Tensor k-mode Unfolding of DelayedArray

In rikenbit/DelayedTensor: R package for sparse and out-of-core arithmetic and decomposition of Tensor

Tensor k-mode Unfolding of DelayedArray

Description

Unfolding of a tensor by mapping the kth mode (specified through parameter m), and all other modes onto the column space. This the most common type of unfolding operation for Tucker decompositions and its variants. Also known as k-mode matricization.

Usage

k_unfold(darr, m)

## S4 method for signature 'DelayedArray'
k_unfold(darr, m)

Arguments

darr	DelayedArray object
m	the index of the mode to unfold on

Details

This function is an extension of the k_unfold by DelayedArray.

This is a wrapper function to unfold.

See also k_unfold(darr, m=NULL)

Value

matrix with dim(darr)[m] rows and prod(dim(darr)[-m]) columns

References

T. Kolda, B. Bader, "Tensor decomposition and applications". SIAM Applied Mathematics and Applications 2009.

See Also

unfold, k_fold

Examples

library("DelayedRandomArray")
darr <- RandomUnifArray(c(2,3,4))
rs_unfold(darr, m=2)

rikenbit/DelayedTensor documentation built on Jan. 30, 2023, 6:15 p.m.