Post date: 15-sep-2014 6:17:36

Title: Hierarchical Quasi-Clustering Methods for Asymmetric Networks

Date: 22-May-2014

Material: slides pdf, Videos

Speaker: Santiago Segarra ( PhD candidate at Univ. Pennsylvania)

Abstract: We introduce hierarchical quasi-clustering methods, a generalization of hierarchical clustering for asymmetric networks where the output structure preserves the asymmetry of the input data. We show that this output structure is equivalent to a finite quasi-ultrametric space and study admissibility with respect to two desirable properties. We prove that a modified version of single linkage is the only admissible quasi-clustering method. Moreover, we show stability of the proposed method and we establish invariance properties fulfilled by it. Algorithms are further developed and the value of quasi-clustering analysis is illustrated with a study of internal migration within United States.

Short Bio: Santiago Segarra is a PhD candidate in Electrical and Systems Engineering at the University of Pennsylvania. He received an Industrial Engineering undergraduate degree from the Buenos Aires Institute of Technology in 2010. Before entering the PhD program, he worked in strategic consulting for Bain & Company for 6 months.

His research interests include optimization, network theory in general with a special interest for topological methods, machine learning and game theory in networks.