get_voronoi_feature

add_new_point_iKernel

The function to get feature representation in RKHS based on Voronoi diagram for WHOLE dataset

internal

Incorporates Approximate Bayesian Computation to get a posterior distribution and to select a model optimal parameter for an observation point. Additionally, the meta-sampling heuristic algorithm is realized for parameter estimation, which requires no model runs and is dimension-independent. A sampling scheme is also presented that allows model runs and uses the meta-sampling for point generation. A predictor is realized as the meta-sampling for the model output. All the algorithms leverage a machine learning method utilizing the maxima weighted Isolation Kernel approach, or 'MaxWiK'. The method involves transforming raw data to a Hilbert space (mapping) and measuring the similarity between simulated points and the maxima weighted Isolation Kernel mapping corresponding to the observation point. Comprehensive details of the methodology can be found in the papers Iurii Nagornov (2024) <doi:10.1007/978-3-031-66431-1_16> and Iurii Nagornov (2023) <doi:10.1007/978-3-031-29168-5_18>.

Yuri Nagornov

MaxWiK

Machine Learning Method Based on Isolation Kernel Mean Embedding

get_voronoi_feature function

<dl><dt>psi</dt>
<dd>Integer number related to the size of each Voronoi diagram</dd>
<dt>t</dt>
<dd>Integer number of trees in Isolation Kernel or dimension of RKHS</dd>
<dt>data</dt>
<dd>dataset of points, rows - points, columns - dimensions of a point</dd>
<dt>talkative</dt>
<dd>logical. If TRUE then print messages, FALSE for the silent execution</dd>
<dt>Matrix_Voronoi</dt>
<dd>Matrix of Voronoi diagrams, if it is NULL then the function will calculate Matrix_Voronoi</dd>
<dt>d1</dt>
<dd>Data point - usually it is an observation data point</dd>
<dt>dissim</dt>
<dd>Matrix of dissimilarity or distances between all points.</dd>
<dt>nr</dt>
<dd>Integer number of rows in matrix of distances (dissim) and also the size of dataset</dd></dl>

Arguments

<ul>
<li><code>add_new_point_iKernel()</code>: The function to get RKHS mapping based on Isolation Kernel for a new point</li>
</ul>

Functions

The function to get feature representation in RKHS based on Voronoi diagram for WHOLE dataset — get_voronoi_feature

<dl>

<dt>psi</dt>
<dd>Integer number related to the size of each Voronoi diagram</dd>


<dt>t</dt>
<dd>Integer number of trees in Isolation Kernel or dimension of RKHS</dd>


<dt>data</dt>
<dd>dataset of points, rows - points, columns - dimensions of a point</dd>


<dt>talkative</dt>
<dd>logical. If TRUE then print messages, FALSE for the silent execution</dd>


<dt>Matrix_Voronoi</dt>
<dd>Matrix of Voronoi diagrams, if it is NULL then the function will calculate Matrix_Voronoi</dd>


<dt>d1</dt>
<dd>Data point - usually it is an observation data point</dd>


<dt>dissim</dt>
<dd>Matrix of dissimilarity or distances between all points.</dd>


<dt>nr</dt>
<dd>Integer number of rows in matrix of distances (dissim) and also the size of dataset</dd>

</dl>

get_voronoi_feature: The function to get feature representation in RKHS based on Voronoi diagram for WHOLE dataset

Description

Usage

Value

Arguments

Functions

Examples