Please use this identifier to cite or link to this item: http://arks.princeton.edu/ark:/88435/dsp01pn89d905t
 Title: Replicated Random Graphs under a Mixture of Low-Rank Decompositions with applications to Multiview Network Modeling Authors: Parmar, Viraj Vijay Advisors: Engelhardt, Barbara Contributors: McConnell, Mark Department: Mathematics Class Year: 2016 Abstract: Collections of network-valued data are prevalent in many scientific domains. Popular methods for analysis use averaging techniques to study statistical properties of the collection, leading to the possible loss of information or structure from the underlying distribution. In this paper we investigate a probabilistic framework for inferring global similarities and local deviations in a set of observed networks generated by a common random variable. This approach leverages a recently developed nonparametric Bayesian random graph model using a mixture of low-rank decompositions in order to facilitate both dimensionality reduction and clustering. We formulate the model and derive a Gibbs sampling procedure for posterior inference. Furthermore, we demonstrate a novel application for unsupervised learning in multivew networks. Extent: 25 pages URI: http://arks.princeton.edu/ark:/88435/dsp01pn89d905t Type of Material: Princeton University Senior Theses Language: en_US Appears in Collections: Mathematics, 1934-2016

Files in This Item:
File SizeFormat