Kernel matrix trimming for improved Kernel K-means clustering

Nikolaos Tsapanos, Anastasios Tefas, Nikolaos Nikolaidis, Ioannis Pitas

Research output: Chapter in Book/Report/Conference proceedingConference Contribution (Conference Proceeding)

273 Downloads (Pure)


The Kernel k-Means algorithm for clustering extends the classic k-Means clustering algorithm. It uses the kernel trick to implicitly calculate distances on a higher dimensional space, thus overcoming the classic algorithm's inability to handle data that are not linearly separable. Given a set of n elements to cluster, the n × n kernel matrix is calculated, which contains the dot products in the higher dimensional space of every possible combination of two elements. This matrix is then referenced to calculate the distance between an element and a cluster center, as per classic k-Means. In this paper, we propose a novel algorithm for zeroing elements of the kernel matrix, thus trimming the matrix, which results in reduced memory complexity and improved clustering performance.
Original languageEnglish
Title of host publication2015 IEEE International Conference on Image Processing (ICIP 2015)
Subtitle of host publicationProceedings of a meeting held 27-30 September 2015, Quebec City, Quebec, Canada
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Number of pages5
ISBN (Electronic)9781479983391
ISBN (Print)9781479983407
Publication statusPublished - Jan 2016
Event2015 IEEE International Conference on Image Processing (ICIP) - Quebec City, ON, Canada
Duration: 27 Sep 201530 Sep 2015


Conference2015 IEEE International Conference on Image Processing (ICIP)
CityQuebec City, ON


Dive into the research topics of 'Kernel matrix trimming for improved Kernel K-means clustering'. Together they form a unique fingerprint.

Cite this