Clusters from higher order correlations

DOI10.1016/J.PHYSLETA.2010.02.021MaRDI QIDQ2429637zbMATH OpenOpenAlexFDO

Authors Lawrence S. Schulman

Publication date 30 April 2012

Published in Physics Letters. A (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/0907.0712

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30) Monte Carlo methods (65C05) Lattice systems (Ising, dimer, Potts, etc.) and systems on graphs arising in equilibrium statistical mechanics (82B20) Stochastic methods applied to problems in equilibrium statistical mechanics (82B31) General biostatistics (92B15)

Abstract: Given a set of variables and the correlations among them, we develop a method for finding clustering among the variables. The method takes advantage of information implicit in higher-order (not just pairwise) correlations. The idea is to define a Potts model whose energy is based on the correlations. Each state of this model is a partition of the variables and a Monte Carlo method is used to identify states of lowest energy, those most consistent with the correlations. A set of the 100 or so lowest such partitions is then used to construct a stochastic dynamics (using the adjacency matrix of each partition) whose observable representation gives the clustering. Three examples are studied. For two of them the 3${}^{m}athrmrd$ order correlations are significant for getting the clusters right. The last of these is a toy model of a biological system in which the joint action of several genes or proteins is necessary to accomplish a given process.

Recommendations

• Clusterization of Correlation Functions
• scientific article; zbMATH DE number 2148179
• Correlation clustering
• Correlation clustering
• Correlation Clustering
• Correlation of clusters: partially truncated correlation functions and their decay
• Higher order clustering coefficients in Barabási-Albert networks
• Clustering from ordination
• Cluster correlations, clustering and halo structure
• Correlation clustering on networks

Cites work

• Community structure in social and biological networks
• Dynamical distance: coarse grains, pattern recognition, and network analysis
• Imaging geometry through dynamics: the observable representation
• Low-temperature dynamics of spin glasses: Walking in the energy landscape
• Multidimensional scaling by optimizing goodness of fit to a nonmetric hypothesis
• Quantitative methods for ecological network analysis
• Random graph models of social networks

Cited in

(3)

• Large values of the clustering coefficient
• Cluster adjacency beyond MHV
• From cluster ensemble to structure ensemble

This page was built for publication: Clusters from higher order correlations

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2429637)