Gradient_cpp: Gradient and objective function

In chickn: 'Compressive' Hierarchical Kernel Clustering Toolbox

Description

Global objective function and gradient computations with respect to cluster centroid vectors and their weights.

Usage

Gradient_cpp(x, SK, W, K)

Arguments

x	is a data vector. Its first K*n components are cluster centroids and its last K components are the centroid weights.
SK	is a data sketch vector.
W	is a frequency matrix.
K	is a number of cluster centroids.

Value

• gradient is a gradient vector

• objective is an objective function value \|SK - ∑_{k=1}^K α_k Sketch(c_k, W)\|

chickn documentation built on Jan. 13, 2021, 10:53 p.m.