Prem Gopalan
Address:	35 Olden Street Princeton, NJ 08540, USA
E-Mail:	pgopalan@cs.princeton.edu

I'm at the Statistical Learning at Princeton Group and the S* Network Systems Group (SNS) in the Computer Science Dept.

I'm advised by Prof. David Blei and Prof. Mike Freedman.

I'm a fifth-year PhD student. I joined Princeton after several years at Mazu Networks (now part of Riverbed Technology). I received my M.S. in Computer Science from Purdue University.

Research

I develop probabilistic graphical models and scalable inference algorithms to learn latent structures in large data.

I have developed fast algorithms for finding overlapping communities in network data, an essential step in many scientific analysis. My ongoing work includes scalable, fast algorithms for building recommendation systems, discovering population structure in genotype data, finding popular nodes in network data and bayesian nonparametric statistical models of recommendation data.

For publications, please see my CV or Google scholar.

I recently released the SVINET C++ package for finding overlapping communities on large undirected networks.

Early in my PhD, I was part of the Serval team. I helped build the first version of an end-host stack for a service-centric network architecture.

Teaching

COS 318, Operating Systems, Prof. Andy Bavier, Fall 2010
COS 461, Computer Networks, Prof. Michael Freedman, Spring 2010

Courses

COS 441, Programming Languages, Prof. Andrew Appel, Fall 2009
COS 518, Advanced Operating Systems, Prof. Michael Freedman, Fall 2009
COS 423, Theory of Algorithms, Prof. Robert Tarjan, Spring 2010
COS 451, Computational Geometry, Prof. Bernard Chazelle, Spring 2010
COS 513, Foundations of Probabilistic Modeling, Prof. David Blei, Fall 2010
COS 561, Advanced Computer Networks, Prof. Jennifer Rexford, Fall 2010
COS 597B, Future Datacenter Networks and Systems, Prof. Michael Freedman, Fall 2010
COS 597C, Advanced Methods in Probabilistic Modeling, Prof. David Blei, Fall 2011

Industry experience

At Mazu, I did the research, design and development of the following projects:

• Arena allocation within Glibc malloc() for multi-threaded systems. Used in Mazu products for several years.
• Algorithms for detecting worm signatures seconds after they spread using the Rabin fingerprinting scheme (publication).
• Core algorithms for detecting network problems using time series analysis. (product page)(marketing video).
• Fast IP lookup in the Linux kernel. Used in a DDoS prevention product for several years.