matr

given data and number of clusters K, choose a bandwidth from a
grid according to the MATR algorithm

Implementations several algorithms for kernel k-means. The default
'OTQT' algorithm is a fast alternative to standard implementations of kernel
k-means, particularly in cases with many clusters. For a small number of
clusters, the implemented 'MacQueen' method typically performs the fastest. For
more details and performance evaluations, see Berlinski and Maitra (2025) <doi:10.1002/sam.70032>.

Josh Berlinski

kkmeans

Fast Implementations of Kernel K-Means

matr function

<dl><dt>dat</dt>
<dd>data vector</dd>
<dt>k</dt>
<dd>number of clusters</dd>
<dt>grid</dt>
<dd>parameter grid to search on</dd>
<dt>tol</dt>
<dd>tolerence for choosing the "best" sigma values. Reducing the
tolerance will give larger values of the bandwidth parameter</dd></dl>

Arguments

Estimate the bandwidth parameter for a gaussian kernel using MATr — matr

<dl>

<dt>dat</dt>
<dd>data vector</dd>


<dt>k</dt>
<dd>number of clusters</dd>


<dt>grid</dt>
<dd>parameter grid to search on</dd>


<dt>tol</dt>
<dd>tolerence for choosing the "best" sigma values. Reducing the
tolerance will give larger values of the bandwidth parameter</dd>

</dl>

matr: Estimate the bandwidth parameter for a gaussian kernel using MATr

Description

Usage

Value

Arguments