Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Silva-Sánchez, David, Lederman, Roy R.
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2506.14952
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866916797642440704
author Silva-Sánchez, David
Lederman, Roy R.
author_facet Silva-Sánchez, David
Lederman, Roy R.
contents Clustering and estimating cluster means are core problems in statistics and machine learning, with k-means and Expectation Maximization (EM) being two widely used algorithms. In this work, we provide a theoretical explanation for the failure of k-means in high-dimensional settings with high noise and limited sample sizes, using a simple Gaussian Mixture Model (GMM). We identify regimes where, with high probability, almost every partition of the data becomes a fixed point of the k-means algorithm. This study is motivated by challenges in the analysis of more complex cases, such as masked GMMs, and those arising from applications in Cryo-Electron Microscopy.
format Preprint
id arxiv_https___arxiv_org_abs_2506_14952
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle An Observation on Lloyd's k-Means Algorithm in High Dimensions
Silva-Sánchez, David
Lederman, Roy R.
Machine Learning
Clustering and estimating cluster means are core problems in statistics and machine learning, with k-means and Expectation Maximization (EM) being two widely used algorithms. In this work, we provide a theoretical explanation for the failure of k-means in high-dimensional settings with high noise and limited sample sizes, using a simple Gaussian Mixture Model (GMM). We identify regimes where, with high probability, almost every partition of the data becomes a fixed point of the k-means algorithm. This study is motivated by challenges in the analysis of more complex cases, such as masked GMMs, and those arising from applications in Cryo-Electron Microscopy.
title An Observation on Lloyd's k-Means Algorithm in High Dimensions
topic Machine Learning
url https://arxiv.org/abs/2506.14952