===firstname:
Rich
===firstname3:

===affil6:

===lastname3:

===email:
rblehou@sandia.gov
===keyword_other2:

===lastname6:

===affil5:

===lastname4:

===lastname7:

===affil7:

===postal:
Sandia National Laboratories
Computational Mathematics
MS 1320, P.O. Box 5800
Albuquerque, NM 87185-1320 
===ABSTRACT:
The purpose of my presentation is to investigate classical hypothesis testing for the stochastic two-block model with variable size blocks or communities. This model is idealized but
enables analysis and provides the basis for more sophisticated models. Our results can be used to determine whether an algorithm purporting to determine two communities is distinct from a randomly generated partition of the graph.
===affil3:

===title:
Hypothesis testing for community detection on the stochastic block model
===affil2:
Department of defense
===lastname2:
Cardinal-Stakenas
===firstname4:

===keyword1:
Iterative Linear Algebraic Data Mining Techniques
===workshop:
yes
===lastname:
Lehoucq
===firstname5:

===keyword2:
NOT_SPECIFIED
===otherauths:

===affil4:

===competition:
no
===firstname7:

===firstname6:

===keyword_other1:

===lastname5:

===affilother:

===firstname2:
Adam