PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

A New Quartet Tree Heuristic for Hierarchical Clustering
Rudi Cilibrasi and Paul Vitányi
unpublished yet (in progress) 2005.

Abstract

We present a new quartet tree heuristic for hierarchical clustering from weighted quartet topologies, and a standard manner to derive those from a given distance matrix. We do not assume that there is a true ternary tree that generated the quartet topologies or distances which we wish to recover as closely as possible. Our aim is to just model the input data as faithfully as possible by the quartet tree. Our method is capable of handling up to 60--80 objects in a matter of hours, while no existing quartet heuristic can directly compute a quartet tree of more than about 20--30 objects without running for years. The method is implemented and available as public software.

PDF - Archive staff only - Requires Adobe Acrobat Reader or other PDF viewer.
EPrint Type:Article
Additional Information:we are still refining the exeriments in this paper a bit
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Computational, Information-Theoretic Learning with Statistics
Learning/Statistics & Optimisation
Theory & Algorithms
ID Code:1821
Deposited By:Rudi Cilibrasi
Deposited On:29 November 2005