Saved in:
Bibliographic Details
Main Authors: Javurek, Tomas, Gregor, Michal, Kula, Sebastian, Simko, Marian
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2511.17219
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911278735294464
author Javurek, Tomas
Gregor, Michal
Kula, Sebastian
Simko, Marian
author_facet Javurek, Tomas
Gregor, Michal
Kula, Sebastian
Simko, Marian
contents The paper introduces DelTriC (Delaunay Triangulation Clustering), a clustering algorithm which integrates PCA/UMAP-based projection, Delaunay triangulation, and a novel back-projection mechanism to form clusters in the original high-dimensional space. DelTriC decouples neighborhood construction from decision-making by first triangulating in a low-dimensional proxy to index local adjacency, and then back-projecting to the original space to perform robust edge pruning, merging, and anomaly detection. DelTriC can outperform traditional methods such as k-means, DBSCAN, and HDBSCAN in many scenarios; it is both scalable and accurate, and it also significantly improves outlier detection.
format Preprint
id arxiv_https___arxiv_org_abs_2511_17219
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DelTriC: A Novel Clustering Method with Accurate Outlier
Javurek, Tomas
Gregor, Michal
Kula, Sebastian
Simko, Marian
Machine Learning
The paper introduces DelTriC (Delaunay Triangulation Clustering), a clustering algorithm which integrates PCA/UMAP-based projection, Delaunay triangulation, and a novel back-projection mechanism to form clusters in the original high-dimensional space. DelTriC decouples neighborhood construction from decision-making by first triangulating in a low-dimensional proxy to index local adjacency, and then back-projecting to the original space to perform robust edge pruning, merging, and anomaly detection. DelTriC can outperform traditional methods such as k-means, DBSCAN, and HDBSCAN in many scenarios; it is both scalable and accurate, and it also significantly improves outlier detection.
title DelTriC: A Novel Clustering Method with Accurate Outlier
topic Machine Learning
url https://arxiv.org/abs/2511.17219