MaxWiK1.0.6 package

Machine Learning Method Based on Isolation Kernel Mean Embedding

apply_range

Function to restrict values of the data according with the range for e...

check_numeric_format

Function to check DATA.FRAME

check_packages

Check the installation of packages and attach them with corresponding ...

check_pkg

Check the installation of a package for some functions

get_inverse_GRAM

The function to get inverse Gram matrix

get_kernel_mean_embedding

The function to calculate Maxima weighted kernel mean mapping for Isol...

get_subset_of_feature_map

The function to get subset of points based on feature mapping

GET_SUBSET

The function to get subset with size psi for Voronoi diagram

get_voronoi_feature_PART_dataset

The function to get feature representation in RKHS based on Voronoi di...

get_voronoi_feature

The function to get feature representation in RKHS based on Voronoi di...

get.MaxWiK

Function to get Approximate Bayesian Computation based on Maxima Weigh...

iKernel

Function returns the value of similarity or Isolation KERNEL for TWO p...

MaxWiK_templates

Function to copy the templates from extdata folder in the library to /...

MaxWiK-package

MaxWiK: Machine Learning Method Based on Isolation Kernel Mean Embeddi...

MaxWiK.ggplot.density

Density plot

MSE_sim

The function to get the mean square error values for statistics of sim...

norm_vec

The norm function for vector

read_file

Function to read file

read_hyperparameters

Function to read hyperparameters and their values from the file

restrict_data

Function to restrict data in the size to accelerate the calculations

sampler_MaxWiK

Function to generate parameters and simulate a model based on MaxWiK a...

sudoku

The function to get the best tracer bullets related to kernel mean emb...

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>.

  • Maintainer: Yuri Nagornov
  • License: GPL (>= 3)
  • Last published: 2025-07-07