ase {multiness}R Documentation

Adjacency Spectral Embedding (ASE)

Description

ase calculates the dd-dimensional adjacency spectral embedding of a symmetric n×nn \times n matrix MM.

Usage

ase(M,d)

Arguments

M

A symmetric matrix.

d

A non-negative integer embedding dimension.

Value

An n×dn \times d matrix XX, defined as US1/2U |S|^{1/2} where SS is a diagonal matrix of the dd leading (in absolute value) eigenvalues of MM, and UU is a matrix of the corresponding eigenvectors.

XX has an additional attribute "signs" which gives the sign of the eigenvalue corresponding to each column.

If d=0d=0, ase returns an n×1n \times 1 matrix of zeros.


[Package multiness version 1.0.2 Index]