scvxclust: Sparse Convex Clustering Path

Description

The function estimates the sparse convex clustering path via AMA or ADMM. Required inputs include a data matrix X (rows are samples; columns are features), a vector of weights w, regularization parameters Gamma1, Gamma2 and the adaptive weight Gamma2_weight.

Usage

scvxclust(X, w, Gamma1, Gamma2, Gamma2_weight, nu = 1, tol_abs = 0.001, tol_rel = 1e-04, max_iter = 10000, type = 2, verbose = F, method = "ama", init = NULL)

Arguments

The data matrix to be clustered. The rows are the samples, and the columns are the features.

A vector of nonnegative weights. The ith entry w[i] denotes the weight used between the ith pair of centroids. The weights are in dictionary order.

Gamma1

A regularization parameter controls cluster size .

Gamma2

A regularization parameter controls the number of informative features .

Gamma2_weight

The weight to adaptively penalize the features.

A positive penalty parameter for quadratic deviation term.

tol_abs

The convergence tolerance (absolute).

tol_rel

The convergence tolerance (relative).

max_iter

The maximum number of iterations.

type

An integer indicating the norm used: 2 = 2-norm. (Only L2 norm are supported for now)

verbose

report convergence information

method

method to fit the sparse convex clustering ("ama" or "admm"). Default is ama

init

initial vlaue of the method

Value

U A list of centroid matrices.V A list of centroid difference matrices.Lambda A list of Lagrange multiplier matrices.iters number of iterations.eva the absolute difference of U between two most recent iteration.method fitted method ("ama" or "admm")