Dimensionality Reduction Using pseudo-Boolean polynomials For Cluster Analysis
Abstract
We introduce usage of a reduction property of penalty-based formulation of pseudo-Boolean polynomials as a mechanism for invariant dimensionality reduction in cluster analysis processes. In our experiments, we show that multidimensional data, like 4-dimensional Iris Flower dataset can be reduced to 2-dimensional space while the 30-dimensional Wisconsin Diagnostic Breast Cancer (WDBC) dataset can be reduced to 3-dimensional space, and by searching lines or planes that lie between reduced samples we can extract clusters in a linear and unbiased manner with competitive accuracies, reproducibility and clear interpretation.
Keywords
Cite
@article{arxiv.2308.15553,
title = {Dimensionality Reduction Using pseudo-Boolean polynomials For Cluster Analysis},
author = {Tendai Mapungwana Chikake and Boris Goldengorin},
journal= {arXiv preprint arXiv:2308.15553},
year = {2023}
}
Comments
14 pages, 4 figures, submitted to the International Conference Data Analysis, Optimization and Their Applications on the Occasion of Boris Mirkin's 80th Birthday January 30-31, 2023, Dolgoprudny, Moscow Region, Moscow Institute of Physics and Technology https://mipt.ru/education/chairs/dm/conferences/data-analysis-optimization-and-their-applications-2023.php