Clustering by principal component analysis with Gaussian kernel in high-dimension, low-sample-size settings

In this paper, we consider clustering based on the kernel principal component analysis (KPCA) for high-dimension, low-sample-size (HDLSS) data. We give theoretical reasons why the Gaussian kernel is effective for clustering high-dimensional data. In addition, we discuss a choice of the scale parameter yielding a high performance of the KPCA with the Gaussian kernel. Finally, we test the performance of the clustering by using microarray data sets. (C) 2021 The Author(s). Published by Elsevier Inc.

Automated summary

This paper examines clustering based on kernel principal component analysis (KPCA) for high-dimension, low-sample-size (HDLSS) data. The study provides theoretical reasons for the effectiveness of the Gaussian kernel in clustering high-dimensional data, and explores the choice of scale parameter for optimal KPCA performance with the Gaussian kernel. Finally, the clustering performance is tested using microarray data sets.