Statistical methods for social networks

Network analysis and modeling have received considerable attention in recent times and require the solution of intricate mathematical problems, e.g. the problem of enumeration graphs under specified conditions, finding the largest complete graph and so on. Even though a lot of well-known algorithms have been proposed, some problems are still challenges from a computational point of view and their fast solutions are thus of great practical interest. This paper focuses on some parallel algorithms for social network analysis. In particular, a review of some existing parallel algorithms is carried out and a new parallel algorithm is proposed for parameters estimation in Exponential Random Graph Models.