sparse_weights {CCMMR}

R Documentation

Computation of sparse weight matrix

Description

Construct a sparse weight matrix in a dictionary-of-keys format. Each nonzero weight is computed as exp(-phi * ||x_i - x_j||^2), where the squared Euclidean distance may be scaled by the average squared Euclidean distance, depending on the argument scale.

Usage

sparse_weights(X, k, phi, connected = TRUE, scale = TRUE)

Arguments

X	An n x p numeric matrix. This function assumes that each row represents an object with p attributes.
k	The number of nearest neighbors to be used for non-zero weights.
phi	Tuning parameter of the Gaussian weights. Input should be a nonnegative value.
connected	If TRUE, guarantee a connected structure of the weight matrix by using a symmetric circulant matrix to add nonzero weights. This ensures that groups of observations that would not be connected through weights that are based only on the k nearest neighbors are (indirectly) connected anyway. Default is TRUE.
scale	If TRUE, scale each squared l2-norm by the mean squared l2-norm to ensure scale invariance of the weights. Default is TRUE.

Value

A sparseweights object containing the nonzero weights in dictionary-of-keys format.

Examples

# Load data
data(two_half_moons)
data = as.matrix(two_half_moons)
X = data[, -3]
y = data[, 3]

# Get sparse distances in dictionary of keys format with k = 5 and phi = 8
W = sparse_weights(X, 5, 8.0)

---