School of Technology and Computer Science Seminars

Stochastic Blockmodels of Mixed Membership for Relational Data

by Mr. Swapnil Singone (School of Technology and Computer Science, TIFR)

Friday, November 22, 2013 from to (Asia/Kolkata)
at Colaba Campus ( D-405 (D-Block Seminar Room) )
Description
In this talk I will introduce a class of latent variable models for relational data. Consider the relational data of pairwise measurements, such as presence or absence of links between a pair of objects. These type of data arises in various environments, for example, Web connects pages by links, collection of author-recipient Emails, scientific literature connects papers by citations, and Social Networks.  These models provide exploratory tools for scientific analysis in applications where the observations can be represented as a collection of unipartite graphs. We will also look at a general variational inference algorithm for approximating the intractable posterior distribution.