machine learning

funOCLUST: Clustering Functional Data with Outliers

arXiv:2508.00110

summary

The paper extends the OCLUST algorithm to handle functional data, providing a robust clustering method that can also identify and trim outliers in curve datasets.

Abstract

Functional data present unique challenges for clustering due to their infinite-dimensional nature and potential sensitivity to outliers. An extension of the OCLUST algorithm to the functional setting is proposed to address these issues. The approach leverages the OCLUST framework, creating a robust method to cluster curves and trim outliers. The methodology is evaluated on both simulated and real-world functional datasets, demonstrating strong performance in clustering and outlier identification.

Topics & keywords

#functional data analysis#clustering#outlier detection#robust statistics#algorithmOCLUSTfunctional clusteringtrimmed clusteringrobust clusteringcurve clustering
funOCLUST: Clustering Functional Data with Outliers · wovepaper