Dynamical Random Effects Driven Preferential Attachment Models

Preferential attachment models and their variants have recently received intense attention in several mathematical and scientific literature. Motivated by applications in various fields, we describe a new variant of the preferential attachment model driven by dynamical random effects. The dynamical random effects facilitate incorporation of various latent features amongst vertices which are otherwise hard to model. We study the properties of the new model and establish several interesting universality properties. Using these properties, inference concerning the parameters of the network will be deduced.

Speaker Bio: Dr. Vidyashankar is an Associate Professor in the Department of Statistics at George Mason University. Previously, he was at University of Georgia and Cornell University. His research interest are several and he has contributed in the following areas: 1. Large Deviations and Branching Processes 2. Inference for high-dimensional data analyses. 3. Divergence based robust inference 4. Statistical methods in veterinary Parasitology 5. Inference for Dynamical Random Networks.

Note: Visitors from outside NIST must contact Cathy Graham; (301) 975-3800; at least 24 hours in advance.