University of Minnesota
University Relations
http://www.umn.edu/urelate
612-624-6868
myU OneStop


Go to unit's home.

Home | Seminars and Symposia | Past seminars/symposia: Thursday, May 1, 2014

DTC Seminar Series

Change Point Inference for Time-varying Erdos-Renyi Graphs

by

George Michailidis
University of Michigan

Thursday, May 1, 2014
11:00 a.m. reception
11:30 a.m. seminar

405 Walter Library

George Michailidis

We investigate a model of an Erdos-Renyi graph, where the edges can be in a present/absent state. The states of each edge evolve as a Markov chain independently of the other edges, and whose parameters exhibit a change-point behavior in time. We derive the maximum likelihood estimator for the change-point and characterize its distribution. Depending on a measure of the signal-to-noise ratio present in the data, different limiting regimes emerge. Nevertheless, a unifying adaptive scheme can be used in practice that covers all cases.We illustrate the model and its flexibility on US Congress voting patterns using roll call data.

 

George Michailidis received his Ph.D. in Mathematics from UCLA in 1996 and then did a postdoc in Operations Research at Stanford University. He joined the University of Michigan in 1998, where he is currently a Professor of Statistics and EECS. He is a Fellow of the Institute of Mathematical Statistics and the American Statistical Association, the Editor in Chief of the Electronic Journal of Statistics and has served on the editorial board of many statistics journals. He has repeatedly been a member of the technical program committee for many conferences including, IEEE SmartGrid Comm, ICC, Globecom and ACM KDD. His research interests are in the areas of stochastic network modeling and performance evaluation, queuing analysis and congestion control, statistical modeling and analysis of Internet traffic, network tomography, and analysis of high dimensional data with network structure.